Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5274 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.4252. Min Act: -0.1700
Data Index: 1018452 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.3314. Min Act: -0.1700
Data Index: 4052428 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.3002. Min Act: -0.1700
Data Index: 571698 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.2689. Min Act: -0.1700
Data Index: 8132407 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.2689. Min Act: -0.1700
Data Index: 7449983 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.2689. Min Act: -0.1700
Data Index: 7913279 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.2377. Min Act: -0.1700
Data Index: 121695 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.2377. Min Act: -0.1700
Data Index: 1222231 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.2377. Min Act: -0.1700
Data Index: 6494963 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.2377. Min Act: -0.1700
Data Index: 690525 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.1752. Min Act: -0.1700
Data Index: 6209396 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.1752. Min Act: -0.1700
Data Index: 291834 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.1752. Min Act: -0.1700
Data Index: 1834575 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.1439. Min Act: -0.1700
Data Index: 6466996 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.0814. Min Act: -0.1700
Data Index: 3606240 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.0814. Min Act: -0.1700
Data Index: 1820606 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.0814. Min Act: -0.1700
Data Index: 462828 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.0814. Min Act: -0.1700
Data Index: 420715 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.0814. Min Act: -0.1700
Data Index: 3492538 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4252. Min Range: -4.4252
Max Act: 4.0501. Min Act: -0.1700
Data Index: 1888059 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19