Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.3820. Min Act: -0.1700
Data Index: 3362261 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.3195. Min Act: -0.1700
Data Index: 8754260 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.2257. Min Act: -0.1700
Data Index: 889415 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.2257. Min Act: -0.1700
Data Index: 5555034 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.1945. Min Act: -0.1700
Data Index: 7543203 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.1632. Min Act: -0.1700
Data Index: 3847871 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.1320. Min Act: -0.1700
Data Index: 5540224 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.1007. Min Act: -0.1700
Data Index: 579463 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.0695. Min Act: -0.1700
Data Index: 2349889 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.0382. Min Act: -0.1700
Data Index: 7418471 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.0382. Min Act: -0.1700
Data Index: 5951700 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.0070. Min Act: -0.1700
Data Index: 8464076 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.0070. Min Act: -0.1700
Data Index: 7365937 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3820. Min Range: -6.3820
Max Act: 5.9757. Min Act: -0.1700
Data Index: 315592 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.0070. Min Act: -0.1700
Data Index: 8679340 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3820. Min Range: -6.3820
Max Act: 5.9757. Min Act: -0.1700
Data Index: 3219475 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3820. Min Range: -6.3820
Max Act: 5.9757. Min Act: -0.1700
Data Index: 1437145 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3820. Min Range: -6.3820
Max Act: 6.0695. Min Act: -0.1700
Data Index: 8797417 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3820. Min Range: -6.3820
Max Act: 5.9132. Min Act: -0.1700
Data Index: 7657043 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3820. Min Range: -6.3820
Max Act: 5.9757. Min Act: -0.1700
Data Index: 1672442 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19