Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2834 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.7168. Min Act: -0.1700
Data Index: 1868975 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.7793. Min Act: -0.1700
Data Index: 503610 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.6230. Min Act: -0.1700
Data Index: 5460812 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.5293. Min Act: -0.1700
Data Index: 441741 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.4980. Min Act: -0.1700
Data Index: 2482111 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.4668. Min Act: -0.1700
Data Index: 1100058 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.4980. Min Act: -0.1700
Data Index: 3248537 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.4668. Min Act: -0.1700
Data Index: 6048238 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.4355. Min Act: -0.1700
Data Index: 2900767 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.4043. Min Act: -0.1700
Data Index: 1536356 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.4043. Min Act: -0.1700
Data Index: 6469435 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.3418. Min Act: -0.1700
Data Index: 1789308 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.2793. Min Act: -0.1700
Data Index: 2321721 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.3105. Min Act: -0.1700
Data Index: 6207267 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.3105. Min Act: -0.1700
Data Index: 3144636 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.3105. Min Act: -0.1700
Data Index: 50519 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.2793. Min Act: -0.1700
Data Index: 979348 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.2793. Min Act: -0.1700
Data Index: 1125751 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.2793. Min Act: -0.1700
Data Index: 5461462 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7793. Min Range: -5.7793
Max Act: 5.3105. Min Act: -0.1700
Data Index: 961158 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19