Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0248. Min Range: -5.0248
Max Act: 5.0248. Min Act: -0.1700
Data Index: 5710067 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.8060. Min Act: -0.1700
Data Index: 3854078 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7435. Min Act: -0.1700
Data Index: 5773329 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6498. Min Act: -0.1700
Data Index: 3305586 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6185. Min Act: -0.1700
Data Index: 4966725 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6185. Min Act: -0.1700
Data Index: 3838957 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5872. Min Act: -0.1700
Data Index: 6365300 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6185. Min Act: -0.1700
Data Index: 1243749 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6185. Min Act: -0.1700
Data Index: 3034697 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6185. Min Act: -0.1700
Data Index: 1994256 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5872. Min Act: -0.1700
Data Index: 5557728 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5872. Min Act: -0.1700
Data Index: 1881562 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5872. Min Act: -0.1700
Data Index: 3773310 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5872. Min Act: -0.1700
Data Index: 8196266 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5872. Min Act: -0.1700
Data Index: 5066165 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5560. Min Act: -0.1700
Data Index: 619378 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5560. Min Act: -0.1700
Data Index: 1791540 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5560. Min Act: -0.1700
Data Index: 3992253 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5560. Min Act: -0.1700
Data Index: 5373994 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5247. Min Act: -0.1700
Data Index: 4302581 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19