Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2634 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1066. Min Range: -5.1066
Max Act: 5.1066. Min Act: -0.1700
Data Index: 2257008 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.9816. Min Act: -0.1700
Data Index: 5155710 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1066. Min Range: -5.1066
Max Act: 5.0129. Min Act: -0.1700
Data Index: 6002514 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.9816. Min Act: -0.1700
Data Index: 8716628 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.9816. Min Act: -0.1700
Data Index: 1234503 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.9816. Min Act: -0.1700
Data Index: 8314562 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.9504. Min Act: -0.1700
Data Index: 5382682 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.9504. Min Act: -0.1700
Data Index: 6765196 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.9816. Min Act: -0.1700
Data Index: 7546744 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.9504. Min Act: -0.1700
Data Index: 7832573 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.9191. Min Act: -0.1700
Data Index: 5065241 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.9191. Min Act: -0.1700
Data Index: 3895550 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.8879. Min Act: -0.1700
Data Index: 3853886 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.8879. Min Act: -0.1700
Data Index: 7534896 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.8566. Min Act: -0.1700
Data Index: 3956248 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.9191. Min Act: -0.1700
Data Index: 3607591 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.8566. Min Act: -0.1700
Data Index: 4905315 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.8566. Min Act: -0.1700
Data Index: 358827 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.8566. Min Act: -0.1700
Data Index: 8442833 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1066. Min Range: -5.1066
Max Act: 4.8566. Min Act: -0.1700
Data Index: 5367030 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19