Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1682 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.6289. Min Act: -0.1700
Data Index: 2927365 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.1602. Min Act: -0.1700
Data Index: 5086538 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.1289. Min Act: -0.1700
Data Index: 7169404 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.0977. Min Act: -0.1700
Data Index: 3354588 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.0977. Min Act: -0.1700
Data Index: 5059470 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.0977. Min Act: -0.1700
Data Index: 3407031 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.0664. Min Act: -0.1700
Data Index: 6435053 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.0977. Min Act: -0.1700
Data Index: 6655150 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.0352. Min Act: -0.1700
Data Index: 335384 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.0352. Min Act: -0.1700
Data Index: 7000867 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.0352. Min Act: -0.1700
Data Index: 1982546 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6289. Min Range: -5.6289
Max Act: 5.0039. Min Act: -0.1700
Data Index: 6039811 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6289. Min Range: -5.6289
Max Act: 4.9727. Min Act: -0.1700
Data Index: 4497005 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6289. Min Range: -5.6289
Max Act: 4.9727. Min Act: -0.1700
Data Index: 440399 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6289. Min Range: -5.6289
Max Act: 4.9414. Min Act: -0.1700
Data Index: 3472697 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6289. Min Range: -5.6289
Max Act: 4.9414. Min Act: -0.1700
Data Index: 2474644 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6289. Min Range: -5.6289
Max Act: 4.9414. Min Act: -0.1700
Data Index: 3130432 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6289. Min Range: -5.6289
Max Act: 4.9102. Min Act: -0.1700
Data Index: 2377059 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6289. Min Range: -5.6289
Max Act: 4.9102. Min Act: -0.1700
Data Index: 6289530 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6289. Min Range: -5.6289
Max Act: 4.9102. Min Act: -0.1700
Data Index: 4431506 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19