Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4239 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0459. Min Range: -5.0459
Max Act: 5.0459. Min Act: -0.1700
Data Index: 5626446 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.9209. Min Act: -0.1700
Data Index: 3493161 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.8584. Min Act: -0.1700
Data Index: 4384201 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.8272. Min Act: -0.1700
Data Index: 7858287 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.8272. Min Act: -0.1700
Data Index: 1749244 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.7959. Min Act: -0.1700
Data Index: 5036092 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.7647. Min Act: -0.1700
Data Index: 8573887 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.7334. Min Act: -0.1700
Data Index: 2685072 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.7334. Min Act: -0.1700
Data Index: 5786613 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.7022. Min Act: -0.1700
Data Index: 6073275 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.6397. Min Act: -0.1700
Data Index: 8530221 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.6084. Min Act: -0.1700
Data Index: 6372329 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.5772. Min Act: -0.1700
Data Index: 716966 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.5459. Min Act: -0.1700
Data Index: 4033041 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.5459. Min Act: -0.1700
Data Index: 8582042 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.5147. Min Act: -0.1700
Data Index: 8426232 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.5147. Min Act: -0.1700
Data Index: 435195 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.5147. Min Act: -0.1700
Data Index: 3406232 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.5147. Min Act: -0.1700
Data Index: 2760255 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0459. Min Range: -5.0459
Max Act: 4.4834. Min Act: -0.1700
Data Index: 8063314 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19