Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3530 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3158. Min Range: -6.3158
Max Act: 6.3158. Min Act: -0.1700
Data Index: 5682316 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3158. Min Range: -6.3158
Max Act: 6.0971. Min Act: -0.1700
Data Index: 3299452 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3158. Min Range: -6.3158
Max Act: 6.0658. Min Act: -0.1700
Data Index: 7707726 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3158. Min Range: -6.3158
Max Act: 6.0346. Min Act: -0.1700
Data Index: 7707724 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.9408. Min Act: -0.1700
Data Index: 7707719 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.8783. Min Act: -0.1700
Data Index: 7707721 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.8158. Min Act: -0.1700
Data Index: 7423882 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.8158. Min Act: -0.1700
Data Index: 7611866 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.7846. Min Act: -0.1700
Data Index: 1149324 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.7533. Min Act: -0.1700
Data Index: 3734337 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.7221. Min Act: -0.1700
Data Index: 6063443 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.7533. Min Act: -0.1700
Data Index: 4225489 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.6908. Min Act: -0.1700
Data Index: 7707725 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.6908. Min Act: -0.1700
Data Index: 4357302 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.6908. Min Act: -0.1700
Data Index: 3304331 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.6908. Min Act: -0.1700
Data Index: 1272579 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.6596. Min Act: -0.1700
Data Index: 6380304 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.6596. Min Act: -0.1700
Data Index: 1088289 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.6596. Min Act: -0.1700
Data Index: 5244246 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3158. Min Range: -6.3158
Max Act: 5.6596. Min Act: -0.1700
Data Index: 4375639 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19