Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3691 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8963. Min Act: -0.1700
Data Index: 638116 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8651. Min Act: -0.1700
Data Index: 4304952 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8651. Min Act: -0.1700
Data Index: 7115564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8338. Min Act: -0.1700
Data Index: 8035801 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8338. Min Act: -0.1700
Data Index: 2061146 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8338. Min Act: -0.1700
Data Index: 8459185 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8338. Min Act: -0.1700
Data Index: 563445 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8338. Min Act: -0.1699
Data Index: 6798411 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8338. Min Act: -0.1700
Data Index: 6450906 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8338. Min Act: -0.1700
Data Index: 6226462 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8338. Min Act: -0.1700
Data Index: 5991838 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8338. Min Act: -0.1700
Data Index: 4460505 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8338. Min Act: -0.1700
Data Index: 2987844 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8025. Min Act: -0.1700
Data Index: 1389671 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8025. Min Act: -0.1700
Data Index: 1513232 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8025. Min Act: -0.1700
Data Index: 1621257 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8025. Min Act: -0.1700
Data Index: 2091969 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8025. Min Act: -0.1700
Data Index: 2423986 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.7712. Min Act: -0.1700
Data Index: 2661221 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8963. Min Range: -3.8963
Max Act: 3.8025. Min Act: -0.1700
Data Index: 544870 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19