Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3863 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.9927. Min Act: -0.1700
Data Index: 8009994 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.9927. Min Act: -0.1700
Data Index: 4663895 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.8677. Min Act: -0.1700
Data Index: 778828 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.7427. Min Act: -0.1700
Data Index: 615540 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.6802. Min Act: -0.1700
Data Index: 3585917 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.5552. Min Act: -0.1700
Data Index: 3616869 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.5552. Min Act: -0.1700
Data Index: 3994996 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.4927. Min Act: -0.1700
Data Index: 6541243 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.3677. Min Act: -0.1700
Data Index: 7728978 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.3052. Min Act: -0.1700
Data Index: 1255282 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.2427. Min Act: -0.1700
Data Index: 1263072 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.2740. Min Act: -0.1700
Data Index: 8779776 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.1177. Min Act: -0.1700
Data Index: 7227779 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.1490. Min Act: -0.1700
Data Index: 5402463 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.1177. Min Act: -0.1700
Data Index: 7650430 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.1490. Min Act: -0.1700
Data Index: 4642160 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.0865. Min Act: -0.1700
Data Index: 8030043 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.0552. Min Act: -0.1700
Data Index: 640888 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9927. Min Range: -8.9927
Max Act: 8.0865. Min Act: -0.1700
Data Index: 1440420 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9927. Min Range: -8.9927
Max Act: 7.9927. Min Act: -0.1700
Data Index: 1446709 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19