Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1399. Min Range: -6.1399
Max Act: 6.1399. Min Act: -0.1700
Data Index: 4044941 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1399. Min Range: -6.1399
Max Act: 6.0149. Min Act: -0.1700
Data Index: 3428918 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.9524. Min Act: -0.1700
Data Index: 2545227 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.8274. Min Act: -0.1700
Data Index: 2523226 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.8274. Min Act: -0.1700
Data Index: 239003 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.7962. Min Act: -0.1700
Data Index: 2110935 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.7337. Min Act: -0.1700
Data Index: 469681 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.7337. Min Act: -0.1700
Data Index: 1796016 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.7024. Min Act: -0.1700
Data Index: 3374662 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.7337. Min Act: -0.1700
Data Index: 5984308 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.6712. Min Act: -0.1700
Data Index: 7304348 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.6712. Min Act: -0.1700
Data Index: 985304 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.6712. Min Act: -0.1700
Data Index: 282553 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.6712. Min Act: -0.1700
Data Index: 5965323 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.6399. Min Act: -0.1700
Data Index: 329916 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.6399. Min Act: -0.1700
Data Index: 6261172 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.6399. Min Act: -0.1700
Data Index: 3501154 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.6399. Min Act: -0.1700
Data Index: 2338576 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.5774. Min Act: -0.1700
Data Index: 1733034 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1399. Min Range: -6.1399
Max Act: 5.5774. Min Act: -0.1700
Data Index: 4397386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19