Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6200. Min Range: -8.6200
Max Act: 8.6200. Min Act: -0.1700
Data Index: 590626 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6200. Min Range: -8.6200
Max Act: 8.5575. Min Act: -0.1700
Data Index: 4776848 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6200. Min Range: -8.6200
Max Act: 8.3700. Min Act: -0.1700
Data Index: 5828537 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6200. Min Range: -8.6200
Max Act: 8.1200. Min Act: -0.1700
Data Index: 2117578 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6200. Min Range: -8.6200
Max Act: 8.1825. Min Act: -0.1700
Data Index: 4910052 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6200. Min Range: -8.6200
Max Act: 8.1200. Min Act: -0.1700
Data Index: 3012806 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6200. Min Range: -8.6200
Max Act: 8.1200. Min Act: -0.1700
Data Index: 6355594 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6200. Min Range: -8.6200
Max Act: 8.0575. Min Act: -0.1700
Data Index: 1275613 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6200. Min Range: -8.6200
Max Act: 8.0575. Min Act: -0.1700
Data Index: 6806732 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6200. Min Range: -8.6200
Max Act: 7.9325. Min Act: -0.1700
Data Index: 6852293 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6200. Min Range: -8.6200
Max Act: 7.9637. Min Act: -0.1700
Data Index: 5972219 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6200. Min Range: -8.6200
Max Act: 7.9325. Min Act: -0.1700
Data Index: 3999854 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6200. Min Range: -8.6200
Max Act: 7.9012. Min Act: -0.1699
Data Index: 8542120 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6200. Min Range: -8.6200
Max Act: 7.9012. Min Act: -0.1700
Data Index: 6336993 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6200. Min Range: -8.6200
Max Act: 7.9012. Min Act: -0.1700
Data Index: 8104891 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6200. Min Range: -8.6200
Max Act: 7.8700. Min Act: -0.1700
Data Index: 771253 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6200. Min Range: -8.6200
Max Act: 7.8387. Min Act: -0.1700
Data Index: 5014210 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6200. Min Range: -8.6200
Max Act: 7.8387. Min Act: -0.1700
Data Index: 8487493 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6200. Min Range: -8.6200
Max Act: 7.8075. Min Act: -0.1700
Data Index: 1363515 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6200. Min Range: -8.6200
Max Act: 7.8075. Min Act: -0.1700
Data Index: 3928920 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19