Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2081 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5503. Min Range: -9.5503
Max Act: 9.5503. Min Act: -0.1700
Data Index: 2403742 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5503. Min Range: -9.5503
Max Act: 9.3003. Min Act: -0.1700
Data Index: 424086 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5503. Min Range: -9.5503
Max Act: 9.1753. Min Act: -0.1700
Data Index: 807740 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5503. Min Range: -9.5503
Max Act: 9.1128. Min Act: -0.1700
Data Index: 1714602 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5503. Min Range: -9.5503
Max Act: 9.0503. Min Act: -0.1700
Data Index: 5563682 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.8628. Min Act: -0.1700
Data Index: 6219583 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.8628. Min Act: -0.1700
Data Index: 6980806 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.8628. Min Act: -0.1700
Data Index: 7598809 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.7378. Min Act: -0.1700
Data Index: 274451 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.7378. Min Act: -0.1700
Data Index: 1194937 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.7378. Min Act: -0.1700
Data Index: 2228007 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.6753. Min Act: -0.1700
Data Index: 8548944 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.6128. Min Act: -0.1700
Data Index: 2066423 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.6128. Min Act: -0.1700
Data Index: 8720842 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.5503. Min Act: -0.1700
Data Index: 4930876 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.6128. Min Act: -0.1700
Data Index: 4676603 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.5503. Min Act: -0.1700
Data Index: 7977411 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.4878. Min Act: -0.1700
Data Index: 8449322 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.4253. Min Act: -0.1700
Data Index: 514426 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5503. Min Range: -9.5503
Max Act: 8.4878. Min Act: -0.1700
Data Index: 5708462 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19