Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2302 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 15.3503. Min Range: -15.3503
Max Act: 15.3503. Min Act: -0.1700
Data Index: 4675990 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.3503. Min Range: -15.3503
Max Act: 13.5378. Min Act: -0.1700
Data Index: 6611311 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.3503. Min Range: -15.3503
Max Act: 12.7253. Min Act: -0.1700
Data Index: 6546816 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.3503. Min Range: -15.3503
Max Act: 12.6003. Min Act: -0.1700
Data Index: 6825254 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.3503. Min Range: -15.3503
Max Act: 12.4753. Min Act: -0.1700
Data Index: 1122442 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.3503. Min Range: -15.3503
Max Act: 11.4128. Min Act: -0.1700
Data Index: 7558210 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.3503. Min Range: -15.3503
Max Act: 11.6628. Min Act: -0.1700
Data Index: 7485628 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.3503. Min Range: -15.3503
Max Act: 10.4753. Min Act: -0.1700
Data Index: 5605732 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.3503. Min Range: -15.3503
Max Act: 12.1003. Min Act: -0.1700
Data Index: 6451067 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.3503. Min Range: -15.3503
Max Act: 10.9753. Min Act: -0.1700
Data Index: 7073198 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.3503. Min Range: -15.3503
Max Act: 12.1628. Min Act: -0.1700
Data Index: 6451070 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.3503. Min Range: -15.3503
Max Act: 11.5378. Min Act: -0.1700
Data Index: 95267 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.3503. Min Range: -15.3503
Max Act: 11.3503. Min Act: -0.1700
Data Index: 7309009 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.3503. Min Range: -15.3503
Max Act: 11.4128. Min Act: -0.1700
Data Index: 1238697 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.3503. Min Range: -15.3503
Max Act: 11.2878. Min Act: -0.1700
Data Index: 1127652 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.3503. Min Range: -15.3503
Max Act: 10.2253. Min Act: -0.1700
Data Index: 8374009 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.3503. Min Range: -15.3503
Max Act: 11.6003. Min Act: -0.1700
Data Index: 6782981 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.3503. Min Range: -15.3503
Max Act: 10.4128. Min Act: -0.1700
Data Index: 5992161 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.3503. Min Range: -15.3503
Max Act: 11.1003. Min Act: -0.1700
Data Index: 4843288 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.3503. Min Range: -15.3503
Max Act: 11.0378. Min Act: -0.1700
Data Index: 4581424 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19