Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.8597. Min Act: -0.1700
Data Index: 4494035 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.7972. Min Act: -0.1700
Data Index: 991056 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.7972. Min Act: -0.1700
Data Index: 3529232 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.7972. Min Act: -0.1700
Data Index: 4926043 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.6722. Min Act: -0.1700
Data Index: 4047095 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.7347. Min Act: -0.1700
Data Index: 7973870 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.7347. Min Act: -0.1700
Data Index: 3829596 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.7347. Min Act: -0.1700
Data Index: 1627433 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.7972. Min Act: -0.1700
Data Index: 1599241 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.7347. Min Act: -0.1700
Data Index: 4729777 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.7347. Min Act: -0.1700
Data Index: 8831543 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.6722. Min Act: -0.1700
Data Index: 3407633 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.7347. Min Act: -0.1700
Data Index: 6735891 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.6722. Min Act: -0.1700
Data Index: 6401234 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.6722. Min Act: -0.1700
Data Index: 5678364 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.6097. Min Act: -0.1700
Data Index: 827153 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.6722. Min Act: -0.1700
Data Index: 7492572 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.6722. Min Act: -0.1700
Data Index: 5721179 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.6097. Min Act: -0.1700
Data Index: 7511855 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8597. Min Range: -9.8597
Max Act: 9.6097. Min Act: -0.1700
Data Index: 6239234 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19