Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.7325. Min Act: -0.1700
Data Index: 1575883 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.7013. Min Act: -0.1700
Data Index: 5769158 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.6075. Min Act: -0.1700
Data Index: 5471734 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.6075. Min Act: -0.1700
Data Index: 4826832 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.5763. Min Act: -0.1700
Data Index: 458378 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.5450. Min Act: -0.1700
Data Index: 1905129 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.4825. Min Act: -0.1700
Data Index: 137467 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.5138. Min Act: -0.1700
Data Index: 7439982 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.4825. Min Act: -0.1700
Data Index: 2049847 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.5138. Min Act: -0.1700
Data Index: 8631381 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.4825. Min Act: -0.1700
Data Index: 4436295 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.4825. Min Act: -0.1700
Data Index: 1203527 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.4513. Min Act: -0.1700
Data Index: 5957038 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.4513. Min Act: -0.1700
Data Index: 4288041 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.5138. Min Act: -0.1700
Data Index: 432484 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.4513. Min Act: -0.1700
Data Index: 8217165 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.4200. Min Act: -0.1700
Data Index: 976001 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.3888. Min Act: -0.1700
Data Index: 4648976 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.4200. Min Act: -0.1700
Data Index: 1631016 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7325. Min Range: -5.7325
Max Act: 5.4200. Min Act: -0.1700
Data Index: 4349489 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19