Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5236 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2518. Min Range: -7.2518
Max Act: 7.2518. Min Act: -0.1700
Data Index: 1239993 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2518. Min Range: -7.2518
Max Act: 7.1581. Min Act: -0.1700
Data Index: 2408085 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2518. Min Range: -7.2518
Max Act: 7.1268. Min Act: -0.1700
Data Index: 5236050 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2518. Min Range: -7.2518
Max Act: 7.0018. Min Act: -0.1700
Data Index: 1873857 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.8768. Min Act: -0.1700
Data Index: 2359678 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.8768. Min Act: -0.1700
Data Index: 8254222 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.8768. Min Act: -0.1700
Data Index: 8046937 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.8456. Min Act: -0.1700
Data Index: 2920692 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.8456. Min Act: -0.1700
Data Index: 2610679 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.8143. Min Act: -0.1700
Data Index: 1806444 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.7518. Min Act: -0.1700
Data Index: 5509699 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.7206. Min Act: -0.1700
Data Index: 4439068 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.6893. Min Act: -0.1700
Data Index: 4833446 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.6893. Min Act: -0.1700
Data Index: 3825565 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.6893. Min Act: -0.1700
Data Index: 6237263 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.6581. Min Act: -0.1700
Data Index: 5494916 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.6581. Min Act: -0.1700
Data Index: 5133161 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.6581. Min Act: -0.1700
Data Index: 5701630 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.6268. Min Act: -0.1700
Data Index: 8120130 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2518. Min Range: -7.2518
Max Act: 6.5956. Min Act: -0.1700
Data Index: 2439209 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19