Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1378 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.6826. Min Act: -0.1700
Data Index: 8210019 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.5264. Min Act: -0.1700
Data Index: 2595606 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.4951. Min Act: -0.1700
Data Index: 8210020 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.3389. Min Act: -0.1700
Data Index: 7155796 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.2763. Min Act: -0.1700
Data Index: 1971908 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.2451. Min Act: -0.1700
Data Index: 6904591 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.2451. Min Act: -0.1700
Data Index: 7377589 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.1826. Min Act: -0.1700
Data Index: 636927 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.1826. Min Act: -0.1700
Data Index: 3184262 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.1513. Min Act: -0.1700
Data Index: 4040018 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.1826. Min Act: -0.1700
Data Index: 2682198 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.1513. Min Act: -0.1700
Data Index: 7561675 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.1826. Min Act: -0.1700
Data Index: 2449064 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.1201. Min Act: -0.1700
Data Index: 398902 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.1201. Min Act: -0.1700
Data Index: 8678799 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.1201. Min Act: -0.1700
Data Index: 6040849 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.0888. Min Act: -0.1700
Data Index: 1992351 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.0888. Min Act: -0.1700
Data Index: 8213646 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.0888. Min Act: -0.1700
Data Index: 961883 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6826. Min Range: -4.6826
Max Act: 4.0888. Min Act: -0.1700
Data Index: 2566342 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19