Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.3511. Min Act: -0.1700
Data Index: 5147585 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.1940. Min Act: -0.1700
Data Index: 3198446 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.1311. Min Act: -0.1700
Data Index: 69121 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.1153. Min Act: -0.1700
Data Index: 5474583 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.0996. Min Act: -0.1700
Data Index: 7480487 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.1153. Min Act: -0.1700
Data Index: 2368643 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.0680. Min Act: -0.1700
Data Index: 8558892 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.0680. Min Act: -0.1700
Data Index: 307406 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.0680. Min Act: -0.1700
Data Index: 3338094 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.0365. Min Act: -0.1700
Data Index: 1389264 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.0207. Min Act: -0.1700
Data Index: 1926548 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.0207. Min Act: -0.1700
Data Index: 182451 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.0049. Min Act: -0.1700
Data Index: 4508047 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3511. Min Range: -3.3511
Max Act: 3.0049. Min Act: -0.1700
Data Index: 3772104 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3511. Min Range: -3.3511
Max Act: 2.9891. Min Act: -0.1700
Data Index: 7873534 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3511. Min Range: -3.3511
Max Act: 2.9891. Min Act: -0.1700
Data Index: 4319904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3511. Min Range: -3.3511
Max Act: 2.9733. Min Act: -0.1700
Data Index: 3019335 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3511. Min Range: -3.3511
Max Act: 2.9733. Min Act: -0.1700
Data Index: 163920 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3511. Min Range: -3.3511
Max Act: 2.9574. Min Act: -0.1700
Data Index: 4204997 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3511. Min Range: -3.3511
Max Act: 2.9574. Min Act: -0.1700
Data Index: 4869462 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19