Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3411 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1945. Min Range: -7.1945
Max Act: 7.1945. Min Act: -0.1700
Data Index: 389717 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.9445. Min Act: -0.1700
Data Index: 8805835 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.8820. Min Act: -0.1700
Data Index: 5462460 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.8820. Min Act: -0.1700
Data Index: 2413459 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.7883. Min Act: -0.1700
Data Index: 7149194 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.7883. Min Act: -0.1700
Data Index: 7330182 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.7570. Min Act: -0.1700
Data Index: 5174042 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.6945. Min Act: -0.1700
Data Index: 1848937 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.6320. Min Act: -0.1700
Data Index: 2430458 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.6008. Min Act: -0.1700
Data Index: 8066957 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.6008. Min Act: -0.1700
Data Index: 4194710 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.6008. Min Act: -0.1700
Data Index: 7661380 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.5695. Min Act: -0.1700
Data Index: 5085395 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.5695. Min Act: -0.1700
Data Index: 1266576 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.5695. Min Act: -0.1700
Data Index: 4693891 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.5070. Min Act: -0.1700
Data Index: 3211079 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.5070. Min Act: -0.1700
Data Index: 3790342 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.5070. Min Act: -0.1700
Data Index: 7210404 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.5070. Min Act: -0.1700
Data Index: 2520475 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1945. Min Range: -7.1945
Max Act: 6.4758. Min Act: -0.1700
Data Index: 1437302 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19