Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1606 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0378. Min Range: -6.0378
Max Act: 6.0378. Min Act: -0.1700
Data Index: 1128680 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.9753. Min Act: -0.1700
Data Index: 8099577 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.9128. Min Act: -0.1700
Data Index: 5943243 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.9128. Min Act: -0.1700
Data Index: 5868152 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8815. Min Act: -0.1700
Data Index: 4673737 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8190. Min Act: -0.1700
Data Index: 6470341 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8190. Min Act: -0.1700
Data Index: 6660748 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.7565. Min Act: -0.1700
Data Index: 4961704 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.7565. Min Act: -0.1700
Data Index: 7792013 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.7878. Min Act: -0.1700
Data Index: 284053 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.7253. Min Act: -0.1700
Data Index: 5771838 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.7565. Min Act: -0.1700
Data Index: 7944529 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.7565. Min Act: -0.1700
Data Index: 851870 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.7565. Min Act: -0.1699
Data Index: 537309 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.7253. Min Act: -0.1700
Data Index: 6626417 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.7253. Min Act: -0.1700
Data Index: 8186028 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.7253. Min Act: -0.1700
Data Index: 6296020 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.6940. Min Act: -0.1700
Data Index: 7920631 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.6940. Min Act: -0.1700
Data Index: 5572402 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.6940. Min Act: -0.1700
Data Index: 7354087 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19