Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1933 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.7383. Min Act: -0.1700
Data Index: 25974 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.6133. Min Act: -0.1700
Data Index: 6074492 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.5508. Min Act: -0.1700
Data Index: 8325921 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.5508. Min Act: -0.1700
Data Index: 436760 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2695. Min Act: -0.1700
Data Index: 3928913 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2070. Min Act: -0.1700
Data Index: 8817486 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.1758. Min Act: -0.1700
Data Index: 2026102 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.1758. Min Act: -0.1700
Data Index: 6813351 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.1445. Min Act: -0.1700
Data Index: 1435975 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.1445. Min Act: -0.1700
Data Index: 316514 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.1132. Min Act: -0.1700
Data Index: 154971 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.1445. Min Act: -0.1700
Data Index: 436759 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.1132. Min Act: -0.1700
Data Index: 8237929 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.0195. Min Act: -0.1700
Data Index: 2835039 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.0507. Min Act: -0.1700
Data Index: 2208797 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.0195. Min Act: -0.1700
Data Index: 3474077 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.0507. Min Act: -0.1700
Data Index: 5497242 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.0195. Min Act: -0.1700
Data Index: 4715740 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.0507. Min Act: -0.1700
Data Index: 6813350 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7383. Min Range: -4.7383
Max Act: 3.9882. Min Act: -0.1700
Data Index: 2277134 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19