Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 785 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.4318. Min Act: -0.1700
Data Index: 1199451 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.4142. Min Act: -0.1699
Data Index: 1589826 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3877. Min Act: -0.1697
Data Index: 7241996 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3877. Min Act: -0.1700
Data Index: 5646085 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3789. Min Act: -0.1700
Data Index: 8559630 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3613. Min Act: -0.1700
Data Index: 4869292 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3701. Min Act: -0.1669
Data Index: 1075640 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3701. Min Act: -0.1699
Data Index: 4641761 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3613. Min Act: -0.1698
Data Index: 3631379 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3436. Min Act: -0.1699
Data Index: 6903427 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3613. Min Act: -0.1696
Data Index: 8756683 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3613. Min Act: -0.1698
Data Index: 4691226 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3436. Min Act: -0.1652
Data Index: 2123004 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3348. Min Act: -0.1700
Data Index: 4448039 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3348. Min Act: -0.1693
Data Index: 8257003 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3436. Min Act: -0.1700
Data Index: 2553111 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3348. Min Act: -0.1664
Data Index: 5338699 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3348. Min Act: -0.1575
Data Index: 6313360 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3260. Min Act: -0.1697
Data Index: 5611162 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4318. Min Range: -1.4318
Max Act: 1.3260. Min Act: -0.1699
Data Index: 8127240 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19