Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.9411. Min Act: -0.1700
Data Index: 1222247 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.9411. Min Act: -0.1700
Data Index: 3801518 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.8474. Min Act: -0.1700
Data Index: 7159684 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.8474. Min Act: -0.1700
Data Index: 8190094 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.8474. Min Act: -0.1700
Data Index: 3092061 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.8474. Min Act: -0.1700
Data Index: 5291381 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.8474. Min Act: -0.1700
Data Index: 3249043 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.8161. Min Act: -0.1700
Data Index: 2171257 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.8161. Min Act: -0.1700
Data Index: 2824023 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.8161. Min Act: -0.1700
Data Index: 6304376 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.8161. Min Act: -0.1700
Data Index: 801051 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.7849. Min Act: -0.1700
Data Index: 3364979 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.7849. Min Act: -0.1700
Data Index: 8461518 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.7536. Min Act: -0.1700
Data Index: 1510420 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.7536. Min Act: -0.1700
Data Index: 773563 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.7536. Min Act: -0.1700
Data Index: 3252385 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.7536. Min Act: -0.1700
Data Index: 3503162 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.7536. Min Act: -0.1700
Data Index: 5259381 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.7536. Min Act: -0.1700
Data Index: 5259380 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.7224. Min Act: -0.1700
Data Index: 4228097 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19