Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.8474. Min Act: -0.1700
Data Index: 6656374 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.7849. Min Act: -0.1700
Data Index: 8297951 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6286. Min Act: -0.1700
Data Index: 2553517 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6286. Min Act: -0.1700
Data Index: 7744996 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5661. Min Act: -0.1700
Data Index: 7744994 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5973. Min Act: -0.1700
Data Index: 3235289 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5973. Min Act: -0.1700
Data Index: 4544959 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5661. Min Act: -0.1700
Data Index: 6042860 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5661. Min Act: -0.1700
Data Index: 7715282 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5348. Min Act: -0.1700
Data Index: 197100 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5348. Min Act: -0.1700
Data Index: 381934 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5661. Min Act: -0.1700
Data Index: 1154947 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5348. Min Act: -0.1700
Data Index: 1947167 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5348. Min Act: -0.1700
Data Index: 7559684 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5348. Min Act: -0.1700
Data Index: 900763 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5036. Min Act: -0.1700
Data Index: 7129038 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.4723. Min Act: -0.1700
Data Index: 5093232 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.4723. Min Act: -0.1700
Data Index: 2497564 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.4723. Min Act: -0.1700
Data Index: 2870822 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5036. Min Act: -0.1700
Data Index: 5601531 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19