Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2971. Min Range: -6.2971
Max Act: 6.2971. Min Act: -0.1700
Data Index: 6917982 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2971. Min Range: -6.2971
Max Act: 6.2346. Min Act: -0.1700
Data Index: 3370910 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2971. Min Range: -6.2971
Max Act: 6.2346. Min Act: -0.1700
Data Index: 6050103 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2971. Min Range: -6.2971
Max Act: 6.2659. Min Act: -0.1700
Data Index: 3210858 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2971. Min Range: -6.2971
Max Act: 6.1409. Min Act: -0.1700
Data Index: 6625402 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2971. Min Range: -6.2971
Max Act: 6.1409. Min Act: -0.1700
Data Index: 5484410 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.9846. Min Act: -0.1700
Data Index: 8772521 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.9221. Min Act: -0.1700
Data Index: 4761360 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.9221. Min Act: -0.1700
Data Index: 4443928 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.8596. Min Act: -0.1700
Data Index: 2759604 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.8284. Min Act: -0.1700
Data Index: 6332557 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.8909. Min Act: -0.1700
Data Index: 6713169 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.8284. Min Act: -0.1700
Data Index: 543203 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.8284. Min Act: -0.1700
Data Index: 2256342 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.9221. Min Act: -0.1700
Data Index: 779273 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.7971. Min Act: -0.1700
Data Index: 29408 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.7971. Min Act: -0.1700
Data Index: 848022 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.7971. Min Act: -0.1700
Data Index: 6561859 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.7659. Min Act: -0.1700
Data Index: 2700646 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2971. Min Range: -6.2971
Max Act: 5.7346. Min Act: -0.1700
Data Index: 5511163 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19