Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1016 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.9609. Min Act: -0.1700
Data Index: 4484740 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.9609. Min Act: -0.1700
Data Index: 7647719 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.9609. Min Act: -0.1700
Data Index: 2480053 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.7734. Min Act: -0.1700
Data Index: 6171379 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.7422. Min Act: -0.1700
Data Index: 4474193 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.6797. Min Act: -0.1700
Data Index: 3910359 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.6484. Min Act: -0.1700
Data Index: 717867 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.6172. Min Act: -0.1700
Data Index: 898995 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.6172. Min Act: -0.1700
Data Index: 723845 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.5547. Min Act: -0.1700
Data Index: 195153 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.5234. Min Act: -0.1700
Data Index: 7040511 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.5234. Min Act: -0.1700
Data Index: 236492 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.4922. Min Act: -0.1700
Data Index: 137747 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.4609. Min Act: -0.1700
Data Index: 61698 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.4609. Min Act: -0.1700
Data Index: 239052 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.4922. Min Act: -0.1700
Data Index: 3307281 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.4297. Min Act: -0.1700
Data Index: 7010812 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.4297. Min Act: -0.1700
Data Index: 3748120 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.4609. Min Act: -0.1700
Data Index: 814808 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9609. Min Range: -7.9609
Max Act: 7.3984. Min Act: -0.1700
Data Index: 2791569 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19