Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6539. Min Range: -10.6539
Max Act: 10.6539. Min Act: -0.1700
Data Index: 3671311 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6539. Min Range: -10.6539
Max Act: 10.4664. Min Act: -0.1700
Data Index: 2595817 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6539. Min Range: -10.6539
Max Act: 10.3414. Min Act: -0.1700
Data Index: 1848288 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6539. Min Range: -10.6539
Max Act: 10.4039. Min Act: -0.1700
Data Index: 3280518 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6539. Min Range: -10.6539
Max Act: 10.2789. Min Act: -0.1700
Data Index: 5981864 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6539. Min Range: -10.6539
Max Act: 10.1539. Min Act: -0.1700
Data Index: 188119 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6539. Min Range: -10.6539
Max Act: 10.1539. Min Act: -0.1700
Data Index: 4312526 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6539. Min Range: -10.6539
Max Act: 10.0289. Min Act: -0.1700
Data Index: 381399 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.9039. Min Act: -0.1700
Data Index: 4171363 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.9039. Min Act: -0.1700
Data Index: 4777574 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.9039. Min Act: -0.1700
Data Index: 6539377 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.8414. Min Act: -0.1700
Data Index: 4462459 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.8414. Min Act: -0.1700
Data Index: 8280002 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.8414. Min Act: -0.1700
Data Index: 8774297 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.7789. Min Act: -0.1700
Data Index: 5522304 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.7789. Min Act: -0.1700
Data Index: 1492741 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.7789. Min Act: -0.1700
Data Index: 6741391 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.7789. Min Act: -0.1700
Data Index: 6426929 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.7164. Min Act: -0.1700
Data Index: 4719641 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6539. Min Range: -10.6539
Max Act: 9.7789. Min Act: -0.1700
Data Index: 868614 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19