Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1636 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9472. Min Range: -9.9472
Max Act: 9.9472. Min Act: -0.1700
Data Index: 2371976 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9472. Min Range: -9.9472
Max Act: 9.2597. Min Act: -0.1700
Data Index: 8421566 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9472. Min Range: -9.9472
Max Act: 9.1972. Min Act: -0.1700
Data Index: 6499018 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9472. Min Range: -9.9472
Max Act: 9.1972. Min Act: -0.1700
Data Index: 1079303 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.8847. Min Act: -0.1700
Data Index: 8805193 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.8222. Min Act: -0.1700
Data Index: 7325705 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.7597. Min Act: -0.1700
Data Index: 7196162 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.7597. Min Act: -0.1700
Data Index: 7544450 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.7597. Min Act: -0.1698
Data Index: 1772828 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.6972. Min Act: -0.1700
Data Index: 3338985 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.6972. Min Act: -0.1700
Data Index: 8080288 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.5722. Min Act: -0.1700
Data Index: 3372570 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.5722. Min Act: -0.1700
Data Index: 8493425 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.5097. Min Act: -0.1700
Data Index: 881909 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.5097. Min Act: -0.1700
Data Index: 6296543 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.4472. Min Act: -0.1700
Data Index: 4143594 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.5097. Min Act: -0.1700
Data Index: 1655890 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.4472. Min Act: -0.1700
Data Index: 198636 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.4472. Min Act: -0.1700
Data Index: 2544241 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9472. Min Range: -9.9472
Max Act: 8.4472. Min Act: -0.1700
Data Index: 6542204 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19