Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 903 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2238. Min Range: -5.2238
Max Act: 5.2238. Min Act: -0.1700
Data Index: 3088530 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.8488. Min Act: -0.1700
Data Index: 4029593 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.7238. Min Act: -0.1700
Data Index: 8782978 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.7551. Min Act: -0.1700
Data Index: 7054955 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.7238. Min Act: -0.1700
Data Index: 6670734 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.7551. Min Act: -0.1700
Data Index: 1624549 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.7863. Min Act: -0.1700
Data Index: 4776864 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.6926. Min Act: -0.1700
Data Index: 4141163 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.6926. Min Act: -0.1700
Data Index: 3316851 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.6613. Min Act: -0.1700
Data Index: 1434424 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.6613. Min Act: -0.1700
Data Index: 2951657 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.6301. Min Act: -0.1700
Data Index: 7939518 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.6301. Min Act: -0.1700
Data Index: 6001087 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.6613. Min Act: -0.1700
Data Index: 7520323 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.6301. Min Act: -0.1700
Data Index: 3272772 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.5988. Min Act: -0.1700
Data Index: 1894001 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.5988. Min Act: -0.1700
Data Index: 6774267 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.5676. Min Act: -0.1700
Data Index: 3111910 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.5676. Min Act: -0.1700
Data Index: 6168355 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2238. Min Range: -5.2238
Max Act: 4.5676. Min Act: -0.1700
Data Index: 6660079 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19