Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1257 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.8202. Min Act: -0.1700
Data Index: 1399443 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.7577. Min Act: -0.1700
Data Index: 7380189 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.6952. Min Act: -0.1700
Data Index: 7099273 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.6639. Min Act: -0.1700
Data Index: 2516303 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.6639. Min Act: -0.1700
Data Index: 4800715 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.6014. Min Act: -0.1700
Data Index: 7078699 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.6014. Min Act: -0.1700
Data Index: 2752608 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.6014. Min Act: -0.1700
Data Index: 7680070 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.5702. Min Act: -0.1700
Data Index: 5630795 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.4764. Min Act: -0.1700
Data Index: 777587 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.4452. Min Act: -0.1700
Data Index: 4147382 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.4139. Min Act: -0.1700
Data Index: 2064269 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.4139. Min Act: -0.1700
Data Index: 2030433 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.4139. Min Act: -0.1700
Data Index: 7452471 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.4139. Min Act: -0.1700
Data Index: 7494552 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.3827. Min Act: -0.1700
Data Index: 5523968 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.3514. Min Act: -0.1700
Data Index: 7397818 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.3827. Min Act: -0.1700
Data Index: 1202090 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.3514. Min Act: -0.1700
Data Index: 5210114 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8202. Min Range: -5.8202
Max Act: 5.3202. Min Act: -0.1700
Data Index: 5393307 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19