Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.6938. Min Act: -0.1700
Data Index: 4766118 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.5688. Min Act: -0.1700
Data Index: 4673840 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.5688. Min Act: -0.1700
Data Index: 770882 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.4751. Min Act: -0.1700
Data Index: 3784737 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.4751. Min Act: -0.1700
Data Index: 8432354 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.3813. Min Act: -0.1700
Data Index: 2869711 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.3501. Min Act: -0.1700
Data Index: 4482099 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.3501. Min Act: -0.1700
Data Index: 6591042 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.3188. Min Act: -0.1700
Data Index: 5600627 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.2876. Min Act: -0.1700
Data Index: 2003614 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.2876. Min Act: -0.1700
Data Index: 4924010 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.2563. Min Act: -0.1700
Data Index: 3496820 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.2563. Min Act: -0.1700
Data Index: 2073541 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.2876. Min Act: -0.1700
Data Index: 3625957 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.2250. Min Act: -0.1700
Data Index: 1967262 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.2250. Min Act: -0.1700
Data Index: 4693331 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.2250. Min Act: -0.1700
Data Index: 6675829 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.1938. Min Act: -0.1700
Data Index: 7922367 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.2250. Min Act: -0.1700
Data Index: 187757 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6938. Min Range: -4.6938
Max Act: 4.2563. Min Act: -0.1700
Data Index: 5394850 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19