Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4577 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.4383. Min Act: -0.1700
Data Index: 255137 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.3758. Min Act: -0.1700
Data Index: 3951597 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.3133. Min Act: -0.1700
Data Index: 8688520 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.2508. Min Act: -0.1700
Data Index: 2341675 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.2821. Min Act: -0.1700
Data Index: 8216003 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.2196. Min Act: -0.1700
Data Index: 8320333 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.2196. Min Act: -0.1700
Data Index: 97800 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.1883. Min Act: -0.1700
Data Index: 5022442 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.1571. Min Act: -0.1700
Data Index: 5311794 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.1571. Min Act: -0.1700
Data Index: 1060127 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.1571. Min Act: -0.1700
Data Index: 2453769 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.1571. Min Act: -0.1700
Data Index: 3951598 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.1258. Min Act: -0.1700
Data Index: 3149429 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.1258. Min Act: -0.1700
Data Index: 37650 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.1258. Min Act: -0.1700
Data Index: 2233054 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.0946. Min Act: -0.1700
Data Index: 6689031 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.0946. Min Act: -0.1700
Data Index: 5120470 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.0946. Min Act: -0.1700
Data Index: 3372428 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.0946. Min Act: -0.1700
Data Index: 2760459 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4383. Min Range: -4.4383
Max Act: 4.0946. Min Act: -0.1700
Data Index: 1007008 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19