Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4714 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0379. Min Range: -4.0379
Max Act: 4.0379. Min Act: -0.1700
Data Index: 4905954 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0379. Min Range: -4.0379
Max Act: 4.0067. Min Act: -0.1700
Data Index: 5788356 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.9754. Min Act: -0.1700
Data Index: 5788360 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.9442. Min Act: -0.1700
Data Index: 4905957 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.9442. Min Act: -0.1700
Data Index: 1649667 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.9442. Min Act: -0.1700
Data Index: 1649666 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.9129. Min Act: -0.1700
Data Index: 1649663 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.9129. Min Act: -0.1700
Data Index: 1649664 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.9442. Min Act: -0.1700
Data Index: 5660865 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.8504. Min Act: -0.1700
Data Index: 7035367 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.8504. Min Act: -0.1700
Data Index: 4611025 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.8191. Min Act: -0.1700
Data Index: 4905956 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.8191. Min Act: -0.1700
Data Index: 66252 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.8191. Min Act: -0.1700
Data Index: 66257 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.8191. Min Act: -0.1700
Data Index: 1649665 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7878. Min Act: -0.1700
Data Index: 3942793 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7878. Min Act: -0.1700
Data Index: 5788357 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7878. Min Act: -0.1700
Data Index: 3942791 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7878. Min Act: -0.1700
Data Index: 4905955 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7878. Min Act: -0.1700
Data Index: 371266 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19