Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.6423. Min Act: -0.1700
Data Index: 5784247 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.6110. Min Act: -0.1700
Data Index: 4724526 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.5173. Min Act: -0.1700
Data Index: 7726611 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.5485. Min Act: -0.1700
Data Index: 7617195 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.5798. Min Act: -0.1700
Data Index: 8398027 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.4860. Min Act: -0.1700
Data Index: 5942325 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.4860. Min Act: -0.1700
Data Index: 1570914 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.4548. Min Act: -0.1700
Data Index: 1853949 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.4860. Min Act: -0.1700
Data Index: 4141590 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.4860. Min Act: -0.1700
Data Index: 5942670 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.4235. Min Act: -0.1700
Data Index: 3281463 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.4235. Min Act: -0.1700
Data Index: 7544066 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.3923. Min Act: -0.1700
Data Index: 510810 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.3923. Min Act: -0.1700
Data Index: 2287563 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.3923. Min Act: -0.1700
Data Index: 6812058 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.3610. Min Act: -0.1700
Data Index: 1843267 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.3298. Min Act: -0.1700
Data Index: 6639925 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.3298. Min Act: -0.1700
Data Index: 5942180 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.3298. Min Act: -0.1700
Data Index: 1352418 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6423. Min Range: -5.6423
Max Act: 5.3298. Min Act: -0.1700
Data Index: 8685957 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19