Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2850 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.6966. Min Act: -0.1700
Data Index: 800085 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.6654. Min Act: -0.1700
Data Index: 6135655 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.6654. Min Act: -0.1700
Data Index: 1791120 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.6341. Min Act: -0.1700
Data Index: 8069100 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.6341. Min Act: -0.1700
Data Index: 7052027 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.6341. Min Act: -0.1700
Data Index: 4113189 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.6029. Min Act: -0.1700
Data Index: 1349893 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.5091. Min Act: -0.1700
Data Index: 5426978 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.5091. Min Act: -0.1700
Data Index: 1900037 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.4466. Min Act: -0.1700
Data Index: 472667 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.4154. Min Act: -0.1700
Data Index: 7800234 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.3841. Min Act: -0.1700
Data Index: 161486 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.3841. Min Act: -0.1700
Data Index: 2096001 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.4154. Min Act: -0.1700
Data Index: 2628304 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.3841. Min Act: -0.1700
Data Index: 3579640 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.3529. Min Act: -0.1700
Data Index: 8399932 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.3529. Min Act: -0.1700
Data Index: 3929235 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.3216. Min Act: -0.1700
Data Index: 3862648 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.3216. Min Act: -0.1700
Data Index: 777508 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6966. Min Range: -6.6966
Max Act: 6.3216. Min Act: -0.1700
Data Index: 6702869 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19