Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3768 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2114. Min Range: -6.2114
Max Act: 6.2114. Min Act: -0.1700
Data Index: 4717367 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2114. Min Range: -6.2114
Max Act: 6.1801. Min Act: -0.1700
Data Index: 5511195 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2114. Min Range: -6.2114
Max Act: 6.1176. Min Act: -0.1700
Data Index: 4850315 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2114. Min Range: -6.2114
Max Act: 6.1801. Min Act: -0.1700
Data Index: 5920278 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2114. Min Range: -6.2114
Max Act: 6.0864. Min Act: -0.1700
Data Index: 7761151 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2114. Min Range: -6.2114
Max Act: 6.0864. Min Act: -0.1700
Data Index: 1683188 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2114. Min Range: -6.2114
Max Act: 6.0239. Min Act: -0.1700
Data Index: 5894666 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.9926. Min Act: -0.1700
Data Index: 3462805 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.9926. Min Act: -0.1700
Data Index: 4451084 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.9301. Min Act: -0.1700
Data Index: 3863472 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.9614. Min Act: -0.1700
Data Index: 4020433 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.9614. Min Act: -0.1700
Data Index: 6878668 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.9301. Min Act: -0.1700
Data Index: 5938345 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.9301. Min Act: -0.1700
Data Index: 8421690 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.9301. Min Act: -0.1700
Data Index: 3143090 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.9301. Min Act: -0.1700
Data Index: 5138766 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.8676. Min Act: -0.1700
Data Index: 2450054 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.8989. Min Act: -0.1700
Data Index: 1089628 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.8676. Min Act: -0.1700
Data Index: 6786552 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2114. Min Range: -6.2114
Max Act: 5.8676. Min Act: -0.1700
Data Index: 3179991 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19