Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6312 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.8564. Min Act: -0.1700
Data Index: 6502674 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.3564. Min Act: -0.1700
Data Index: 8025997 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.2314. Min Act: -0.1700
Data Index: 5119148 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.2001. Min Act: -0.1700
Data Index: 6151208 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.2001. Min Act: -0.1700
Data Index: 3701758 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.1376. Min Act: -0.1700
Data Index: 1034712 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.1376. Min Act: -0.1700
Data Index: 4920922 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.1064. Min Act: -0.1700
Data Index: 4941107 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.1064. Min Act: -0.1700
Data Index: 8087337 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.0751. Min Act: -0.1700
Data Index: 6077150 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.0751. Min Act: -0.1700
Data Index: 7043772 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.0751. Min Act: -0.1700
Data Index: 3489079 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.0751. Min Act: -0.1700
Data Index: 8295125 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.0751. Min Act: -0.1700
Data Index: 2514758 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.0126. Min Act: -0.1700
Data Index: 3155888 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8564. Min Range: -7.8564
Max Act: 7.0126. Min Act: -0.1700
Data Index: 8312320 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8564. Min Range: -7.8564
Max Act: 6.9814. Min Act: -0.1700
Data Index: 1946171 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8564. Min Range: -7.8564
Max Act: 6.9501. Min Act: -0.1700
Data Index: 3430089 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8564. Min Range: -7.8564
Max Act: 6.9501. Min Act: -0.1700
Data Index: 5996970 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8564. Min Range: -7.8564
Max Act: 6.9814. Min Act: -0.1700
Data Index: 4438000 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19