Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 662 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1629. Min Range: -10.1629
Max Act: 10.1629. Min Act: -0.1700
Data Index: 5948054 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1629. Min Range: -10.1629
Max Act: 9.4129. Min Act: -0.1700
Data Index: 734087 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1629. Min Range: -10.1629
Max Act: 9.3504. Min Act: -0.1700
Data Index: 195379 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1629. Min Range: -10.1629
Max Act: 9.3504. Min Act: -0.1700
Data Index: 4440701 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1629. Min Range: -10.1629
Max Act: 9.2254. Min Act: -0.1700
Data Index: 5721990 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1629. Min Range: -10.1629
Max Act: 9.2254. Min Act: -0.1700
Data Index: 6078328 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1629. Min Range: -10.1629
Max Act: 9.1629. Min Act: -0.1700
Data Index: 7947241 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1629. Min Range: -10.1629
Max Act: 9.1629. Min Act: -0.1700
Data Index: 6205037 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1629. Min Range: -10.1629
Max Act: 9.1629. Min Act: -0.1700
Data Index: 3514598 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1629. Min Range: -10.1629
Max Act: 9.0379. Min Act: -0.1700
Data Index: 631389 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1629. Min Range: -10.1629
Max Act: 8.9754. Min Act: -0.1700
Data Index: 453555 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1629. Min Range: -10.1629
Max Act: 8.9754. Min Act: -0.1700
Data Index: 8208412 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1629. Min Range: -10.1629
Max Act: 8.9129. Min Act: -0.1700
Data Index: 2267471 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1629. Min Range: -10.1629
Max Act: 8.9754. Min Act: -0.1700
Data Index: 600605 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1629. Min Range: -10.1629
Max Act: 8.9129. Min Act: -0.1700
Data Index: 4601664 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1629. Min Range: -10.1629
Max Act: 8.9129. Min Act: -0.1700
Data Index: 2354772 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1629. Min Range: -10.1629
Max Act: 8.9129. Min Act: -0.1700
Data Index: 7772201 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1629. Min Range: -10.1629
Max Act: 8.9129. Min Act: -0.1700
Data Index: 574566 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1629. Min Range: -10.1629
Max Act: 8.9129. Min Act: -0.1700
Data Index: 977781 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1629. Min Range: -10.1629
Max Act: 8.8504. Min Act: -0.1700
Data Index: 5413862 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19