Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4482 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8243. Min Range: -7.8243
Max Act: 7.8243. Min Act: -0.1700
Data Index: 6346062 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8243. Min Range: -7.8243
Max Act: 7.5743. Min Act: -0.1700
Data Index: 323336 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8243. Min Range: -7.8243
Max Act: 7.1681. Min Act: -0.1700
Data Index: 8166850 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8243. Min Range: -7.8243
Max Act: 7.1681. Min Act: -0.1700
Data Index: 4962516 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8243. Min Range: -7.8243
Max Act: 7.1056. Min Act: -0.1700
Data Index: 3420789 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8243. Min Range: -7.8243
Max Act: 7.1056. Min Act: -0.1700
Data Index: 2810605 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8243. Min Range: -7.8243
Max Act: 7.0431. Min Act: -0.1700
Data Index: 5382196 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8243. Min Range: -7.8243
Max Act: 7.0118. Min Act: -0.1700
Data Index: 115866 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8243. Min Range: -7.8243
Max Act: 7.0118. Min Act: -0.1700
Data Index: 1081461 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8243. Min Range: -7.8243
Max Act: 6.9493. Min Act: -0.1700
Data Index: 29864 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8243. Min Range: -7.8243
Max Act: 6.9493. Min Act: -0.1700
Data Index: 686241 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8243. Min Range: -7.8243
Max Act: 6.9493. Min Act: -0.1700
Data Index: 7133773 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8243. Min Range: -7.8243
Max Act: 6.9493. Min Act: -0.1700
Data Index: 3051074 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8243. Min Range: -7.8243
Max Act: 6.9493. Min Act: -0.1700
Data Index: 6693988 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8243. Min Range: -7.8243
Max Act: 6.9181. Min Act: -0.1700
Data Index: 7161201 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8243. Min Range: -7.8243
Max Act: 6.9181. Min Act: -0.1700
Data Index: 5922171 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8243. Min Range: -7.8243
Max Act: 6.9181. Min Act: -0.1700
Data Index: 4237168 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8243. Min Range: -7.8243
Max Act: 6.8868. Min Act: -0.1700
Data Index: 3743871 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8243. Min Range: -7.8243
Max Act: 6.8868. Min Act: -0.1700
Data Index: 4185959 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8243. Min Range: -7.8243
Max Act: 6.8868. Min Act: -0.1700
Data Index: 4806658 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19