Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1258 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.3664. Min Act: -0.1700
Data Index: 4693016 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.3039. Min Act: -0.1700
Data Index: 707332 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.1789. Min Act: -0.1700
Data Index: 5320553 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.1789. Min Act: -0.1700
Data Index: 157802 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.1476. Min Act: -0.1700
Data Index: 7984080 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.1164. Min Act: -0.1700
Data Index: 1725071 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.1164. Min Act: -0.1700
Data Index: 7350342 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0851. Min Act: -0.1700
Data Index: 6898533 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0851. Min Act: -0.1700
Data Index: 834892 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0851. Min Act: -0.1700
Data Index: 7568199 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0851. Min Act: -0.1700
Data Index: 6015726 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0851. Min Act: -0.1700
Data Index: 5948817 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0851. Min Act: -0.1700
Data Index: 4864751 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0851. Min Act: -0.1700
Data Index: 7351643 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0539. Min Act: -0.1700
Data Index: 4864753 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0539. Min Act: -0.1700
Data Index: 6931768 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0539. Min Act: -0.1700
Data Index: 4251254 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0539. Min Act: -0.1700
Data Index: 7911664 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0226. Min Act: -0.1700
Data Index: 7517632 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3664. Min Range: -5.3664
Max Act: 5.0226. Min Act: -0.1700
Data Index: 6931590 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19