Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 959 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0281. Min Range: -5.0281
Max Act: 5.0281. Min Act: -0.1700
Data Index: 6381056 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.9969. Min Act: -0.1700
Data Index: 4944712 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.9656. Min Act: -0.1700
Data Index: 2759053 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.9344. Min Act: -0.1700
Data Index: 4622647 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.8719. Min Act: -0.1700
Data Index: 8615737 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.8094. Min Act: -0.1700
Data Index: 4944702 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.7781. Min Act: -0.1700
Data Index: 3658909 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.7781. Min Act: -0.1700
Data Index: 5899496 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.7469. Min Act: -0.1700
Data Index: 7600308 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.7469. Min Act: -0.1700
Data Index: 7600304 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.6531. Min Act: -0.1700
Data Index: 1210026 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.6219. Min Act: -0.1700
Data Index: 3244546 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.6531. Min Act: -0.1700
Data Index: 3658917 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.6531. Min Act: -0.1700
Data Index: 8195052 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.5906. Min Act: -0.1700
Data Index: 7608767 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.5906. Min Act: -0.1700
Data Index: 2046315 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.5906. Min Act: -0.1700
Data Index: 8739839 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.5906. Min Act: -0.1700
Data Index: 2859392 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.5281. Min Act: -0.1700
Data Index: 7135773 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0281. Min Range: -5.0281
Max Act: 4.5281. Min Act: -0.1700
Data Index: 6781103 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19