Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 808 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.9228. Min Act: -0.1700
Data Index: 2290417 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.9541. Min Act: -0.1700
Data Index: 7501755 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.9228. Min Act: -0.1700
Data Index: 1305617 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.8916. Min Act: -0.1700
Data Index: 3120355 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.8916. Min Act: -0.1700
Data Index: 1082830 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.8603. Min Act: -0.1700
Data Index: 3824937 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.7978. Min Act: -0.1700
Data Index: 7035876 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.7978. Min Act: -0.1700
Data Index: 4617963 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.7666. Min Act: -0.1700
Data Index: 3184436 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.7666. Min Act: -0.1700
Data Index: 4954830 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.7041. Min Act: -0.1700
Data Index: 7334413 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.7353. Min Act: -0.1700
Data Index: 4090401 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.7353. Min Act: -0.1700
Data Index: 3118006 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.7041. Min Act: -0.1700
Data Index: 7317582 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.7353. Min Act: -0.1700
Data Index: 3153349 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.6728. Min Act: -0.1700
Data Index: 6326789 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.6416. Min Act: -0.1700
Data Index: 513143 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.6416. Min Act: -0.1700
Data Index: 6045371 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.6416. Min Act: -0.1700
Data Index: 6784008 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9541. Min Range: -5.9541
Max Act: 5.6103. Min Act: -0.1700
Data Index: 995300 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19