Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4477 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0170. Min Range: -5.0170
Max Act: 5.0170. Min Act: -0.1700
Data Index: 741569 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.8920. Min Act: -0.1700
Data Index: 4122115 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.8608. Min Act: -0.1700
Data Index: 9115 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.8295. Min Act: -0.1700
Data Index: 405967 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.8295. Min Act: -0.1700
Data Index: 757723 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.7358. Min Act: -0.1700
Data Index: 913033 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.7358. Min Act: -0.1700
Data Index: 1971546 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.7045. Min Act: -0.1700
Data Index: 456431 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.7670. Min Act: -0.1700
Data Index: 3139037 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.7045. Min Act: -0.1700
Data Index: 3600384 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.6733. Min Act: -0.1700
Data Index: 323336 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.6733. Min Act: -0.1700
Data Index: 3563956 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.6420. Min Act: -0.1700
Data Index: 1218681 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.6108. Min Act: -0.1700
Data Index: 1993125 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.6108. Min Act: -0.1700
Data Index: 455026 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.5795. Min Act: -0.1700
Data Index: 2603448 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.5795. Min Act: -0.1700
Data Index: 2108555 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.5483. Min Act: -0.1700
Data Index: 528501 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.5795. Min Act: -0.1700
Data Index: 3786268 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0170. Min Range: -5.0170
Max Act: 4.5795. Min Act: -0.1700
Data Index: 2569532 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19