Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2486 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3281. Min Range: -4.3281
Max Act: 4.3281. Min Act: -0.1700
Data Index: 4675916 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3281. Min Range: -4.3281
Max Act: 4.3281. Min Act: -0.1700
Data Index: 4458983 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3281. Min Range: -4.3281
Max Act: 4.2656. Min Act: -0.1700
Data Index: 3059146 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3281. Min Range: -4.3281
Max Act: 4.1406. Min Act: -0.1700
Data Index: 6596794 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3281. Min Range: -4.3281
Max Act: 4.0781. Min Act: -0.1700
Data Index: 4029902 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3281. Min Range: -4.3281
Max Act: 4.0468. Min Act: -0.1700
Data Index: 5799408 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9843. Min Act: -0.1700
Data Index: 2096948 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9843. Min Act: -0.1700
Data Index: 6904444 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9843. Min Act: -0.1700
Data Index: 7722481 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9531. Min Act: -0.1700
Data Index: 5837104 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9531. Min Act: -0.1700
Data Index: 907467 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9218. Min Act: -0.1700
Data Index: 5192323 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9218. Min Act: -0.1700
Data Index: 2050487 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9218. Min Act: -0.1700
Data Index: 5550865 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9218. Min Act: -0.1700
Data Index: 3686297 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9218. Min Act: -0.1700
Data Index: 2403809 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9531. Min Act: -0.1700
Data Index: 1090495 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.9531. Min Act: -0.1700
Data Index: 8564636 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.8905. Min Act: -0.1700
Data Index: 5099122 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3281. Min Range: -4.3281
Max Act: 3.8593. Min Act: -0.1700
Data Index: 896638 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19