Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3181 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5991. Min Range: -6.5991
Max Act: 6.5991. Min Act: -0.1700
Data Index: 7833258 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8804. Min Act: -0.1700
Data Index: 1982335 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8491. Min Act: -0.1700
Data Index: 974125 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 6828398 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 7416498 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 6815986 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 1929818 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 5976788 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 3877207 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 1104661 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 648753 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 2303807 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 7532870 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 4306582 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.8179. Min Act: -0.1700
Data Index: 5444730 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.7866. Min Act: -0.1700
Data Index: 6361288 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.7866. Min Act: -0.1700
Data Index: 3496650 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.7866. Min Act: -0.1700
Data Index: 2737508 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.7866. Min Act: -0.1700
Data Index: 490642 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5991. Min Range: -6.5991
Max Act: 5.7554. Min Act: -0.1700
Data Index: 787204 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19