Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3321 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.5980. Min Act: -0.1700
Data Index: 1855251 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.5042. Min Act: -0.1700
Data Index: 4559506 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.3167. Min Act: -0.1700
Data Index: 100588 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.2542. Min Act: -0.1700
Data Index: 7658204 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.2230. Min Act: -0.1700
Data Index: 3372938 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.1917. Min Act: -0.1700
Data Index: 4644654 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.1605. Min Act: -0.1700
Data Index: 581764 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.1605. Min Act: -0.1700
Data Index: 238956 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.1605. Min Act: -0.1700
Data Index: 3524566 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.1605. Min Act: -0.1700
Data Index: 147127 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.0667. Min Act: -0.1700
Data Index: 4609223 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.0667. Min Act: -0.1700
Data Index: 5755211 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.0667. Min Act: -0.1700
Data Index: 2843612 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.0355. Min Act: -0.1700
Data Index: 4716684 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.0355. Min Act: -0.1700
Data Index: 5669476 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.0355. Min Act: -0.1700
Data Index: 6617699 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.0355. Min Act: -0.1700
Data Index: 706862 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.0355. Min Act: -0.1700
Data Index: 2416642 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.0042. Min Act: -0.1700
Data Index: 6965255 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5980. Min Range: -5.5980
Max Act: 5.0042. Min Act: -0.1700
Data Index: 1628212 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19