Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2974. Min Range: -4.2974
Max Act: 4.2974. Min Act: -0.1700
Data Index: 8262775 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2974. Min Range: -4.2974
Max Act: 4.2661. Min Act: -0.1700
Data Index: 1855319 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2974. Min Range: -4.2974
Max Act: 4.1098. Min Act: -0.1700
Data Index: 249844 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2974. Min Range: -4.2974
Max Act: 4.1098. Min Act: -0.1700
Data Index: 7172607 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2974. Min Range: -4.2974
Max Act: 4.0786. Min Act: -0.1700
Data Index: 1388501 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2974. Min Range: -4.2974
Max Act: 4.0786. Min Act: -0.1700
Data Index: 3894790 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2974. Min Range: -4.2974
Max Act: 4.0473. Min Act: -0.1700
Data Index: 5339580 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.9848. Min Act: -0.1700
Data Index: 3810064 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.9848. Min Act: -0.1700
Data Index: 6161226 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.9535. Min Act: -0.1700
Data Index: 7632569 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.9848. Min Act: -0.1700
Data Index: 1087093 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.9535. Min Act: -0.1700
Data Index: 1590388 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.9535. Min Act: -0.1700
Data Index: 2383310 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.9223. Min Act: -0.1700
Data Index: 878777 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.9535. Min Act: -0.1700
Data Index: 6731220 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.8910. Min Act: -0.1700
Data Index: 7502259 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.9223. Min Act: -0.1700
Data Index: 386692 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.9223. Min Act: -0.1700
Data Index: 4485389 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.8910. Min Act: -0.1700
Data Index: 610167 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2974. Min Range: -4.2974
Max Act: 3.8910. Min Act: -0.1700
Data Index: 5770008 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19