Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 808 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.3670. Min Act: -0.1700
Data Index: 7236000 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.3357. Min Act: -0.1700
Data Index: 2389594 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.2415. Min Act: -0.1700
Data Index: 719741 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.2415. Min Act: -0.1700
Data Index: 3384930 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.2257. Min Act: -0.1700
Data Index: 3081236 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1786. Min Act: -0.1700
Data Index: 5436695 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1786. Min Act: -0.1700
Data Index: 7269240 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1786. Min Act: -0.1700
Data Index: 6012415 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1786. Min Act: -0.1700
Data Index: 5116399 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1628. Min Act: -0.1700
Data Index: 6108738 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1471. Min Act: -0.1700
Data Index: 719738 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1313. Min Act: -0.1700
Data Index: 5682302 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1471. Min Act: -0.1700
Data Index: 7996381 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1313. Min Act: -0.1700
Data Index: 7525397 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1471. Min Act: -0.1700
Data Index: 6941945 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1471. Min Act: -0.1700
Data Index: 1262211 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.1313. Min Act: -0.1700
Data Index: 5738418 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.0998. Min Act: -0.1700
Data Index: 1553973 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.0841. Min Act: -0.1700
Data Index: 870614 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3670. Min Range: -3.3670
Max Act: 3.0998. Min Act: -0.1700
Data Index: 4965518 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19