Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5894. Min Range: -11.5894
Max Act: 11.5894. Min Act: -0.1700
Data Index: 3791498 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5894. Min Range: -11.5894
Max Act: 11.2769. Min Act: -0.1700
Data Index: 3312134 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.8394. Min Act: -0.1700
Data Index: 5542899 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.7144. Min Act: -0.1700
Data Index: 3668751 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.7769. Min Act: -0.1700
Data Index: 2420721 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.7769. Min Act: -0.1700
Data Index: 8217391 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.7769. Min Act: -0.1700
Data Index: 454892 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.7144. Min Act: -0.1700
Data Index: 8331831 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.6519. Min Act: -0.1700
Data Index: 8452211 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.5894. Min Act: -0.1700
Data Index: 5671577 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.5894. Min Act: -0.1700
Data Index: 4843394 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.5894. Min Act: -0.1700
Data Index: 5098481 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.5894. Min Act: -0.1700
Data Index: 6274014 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.5269. Min Act: -0.1700
Data Index: 2405556 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.5269. Min Act: -0.1700
Data Index: 8120926 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.5269. Min Act: -0.1700
Data Index: 160027 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.5269. Min Act: -0.1700
Data Index: 2794325 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.4644. Min Act: -0.1700
Data Index: 4830000 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.4644. Min Act: -0.1700
Data Index: 946086 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5894. Min Range: -11.5894
Max Act: 10.4644. Min Act: -0.1700
Data Index: 4908910 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19