Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1727 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0359. Min Range: -3.0359
Max Act: 3.0359. Min Act: -0.1700
Data Index: 4112884 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.9569. Min Act: -0.1700
Data Index: 4206572 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.9094. Min Act: -0.1700
Data Index: 7562786 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8777. Min Act: -0.1700
Data Index: 777168 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8935. Min Act: -0.1700
Data Index: 7000963 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8777. Min Act: -0.1700
Data Index: 6285191 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8777. Min Act: -0.1700
Data Index: 6423770 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8777. Min Act: -0.1700
Data Index: 777675 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8618. Min Act: -0.1700
Data Index: 5219433 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8459. Min Act: -0.1700
Data Index: 441450 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8618. Min Act: -0.1700
Data Index: 1069961 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8459. Min Act: -0.1700
Data Index: 156302 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8459. Min Act: -0.1700
Data Index: 4104307 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8618. Min Act: -0.1700
Data Index: 3334357 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8459. Min Act: -0.1700
Data Index: 7195866 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8141. Min Act: -0.1700
Data Index: 2100718 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8459. Min Act: -0.1700
Data Index: 6477787 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.7982. Min Act: -0.1700
Data Index: 7692375 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.8300. Min Act: -0.1700
Data Index: 1911206 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0359. Min Range: -3.0359
Max Act: 2.7982. Min Act: -0.1700
Data Index: 3970345 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19