Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4022 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.9678. Min Act: -0.1700
Data Index: 8395027 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.9053. Min Act: -0.1700
Data Index: 3971234 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.9053. Min Act: -0.1700
Data Index: 7476812 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.8428. Min Act: -0.1700
Data Index: 2602963 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.8428. Min Act: -0.1700
Data Index: 4560763 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.8740. Min Act: -0.1700
Data Index: 859728 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.8115. Min Act: -0.1700
Data Index: 3476990 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.8115. Min Act: -0.1700
Data Index: 3971233 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.8115. Min Act: -0.1700
Data Index: 225101 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.8115. Min Act: -0.1700
Data Index: 4379496 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.7803. Min Act: -0.1700
Data Index: 3897446 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.8115. Min Act: -0.1700
Data Index: 722468 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.8115. Min Act: -0.1700
Data Index: 3116169 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.7803. Min Act: -0.1700
Data Index: 8472701 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.7803. Min Act: -0.1700
Data Index: 397963 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.8115. Min Act: -0.1700
Data Index: 586653 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.7803. Min Act: -0.1700
Data Index: 2081861 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.7490. Min Act: -0.1700
Data Index: 6720436 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.7490. Min Act: -0.1700
Data Index: 7607957 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9678. Min Range: -4.9678
Max Act: 4.7803. Min Act: -0.1700
Data Index: 2486610 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19