Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2360 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.6078. Min Act: -0.1700
Data Index: 279443 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.4669. Min Act: -0.1700
Data Index: 8721934 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.4199. Min Act: -0.1700
Data Index: 5343332 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.4042. Min Act: -0.1700
Data Index: 6986528 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.3258. Min Act: -0.1700
Data Index: 7564318 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.3101. Min Act: -0.1700
Data Index: 7394372 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.3101. Min Act: -0.1700
Data Index: 3944402 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.3101. Min Act: -0.1700
Data Index: 1182229 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.2787. Min Act: -0.1700
Data Index: 7279262 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.2315. Min Act: -0.1700
Data Index: 7796593 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.2001. Min Act: -0.1700
Data Index: 1152280 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.1844. Min Act: -0.1700
Data Index: 6545600 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.1844. Min Act: -0.1700
Data Index: 5805196 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.1529. Min Act: -0.1700
Data Index: 1819006 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.1686. Min Act: -0.1700
Data Index: 6759764 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.1686. Min Act: -0.1700
Data Index: 8762430 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.1372. Min Act: -0.1700
Data Index: 7264024 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.1529. Min Act: -0.1700
Data Index: 5029556 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.1529. Min Act: -0.1700
Data Index: 2892634 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6078. Min Range: -3.6078
Max Act: 3.1529. Min Act: -0.1700
Data Index: 1280154 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19