Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1933. Min Range: -7.1933
Max Act: 7.1933. Min Act: -0.1700
Data Index: 6624166 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1933. Min Range: -7.1933
Max Act: 7.0996. Min Act: -0.1700
Data Index: 7442022 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1933. Min Range: -7.1933
Max Act: 7.0996. Min Act: -0.1700
Data Index: 5603212 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.9746. Min Act: -0.1700
Data Index: 6182942 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.9746. Min Act: -0.1700
Data Index: 7382824 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.8808. Min Act: -0.1700
Data Index: 8125205 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.8808. Min Act: -0.1700
Data Index: 3461095 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.8496. Min Act: -0.1700
Data Index: 425175 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.8496. Min Act: -0.1700
Data Index: 4515870 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.8496. Min Act: -0.1700
Data Index: 233000 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.8183. Min Act: -0.1700
Data Index: 7969099 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.8496. Min Act: -0.1700
Data Index: 6258189 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.7871. Min Act: -0.1700
Data Index: 677812 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.7558. Min Act: -0.1700
Data Index: 1779045 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.7558. Min Act: -0.1700
Data Index: 7360597 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.7246. Min Act: -0.1700
Data Index: 7230108 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.7871. Min Act: -0.1700
Data Index: 6043178 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.7558. Min Act: -0.1700
Data Index: 1739878 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.7558. Min Act: -0.1700
Data Index: 2339954 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1933. Min Range: -7.1933
Max Act: 6.7246. Min Act: -0.1700
Data Index: 4184927 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19