Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0647. Min Range: -7.0647
Max Act: 7.0647. Min Act: -0.1700
Data Index: 4523375 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.8772. Min Act: -0.1700
Data Index: 6291896 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.6585. Min Act: -0.1700
Data Index: 8748683 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.6897. Min Act: -0.1700
Data Index: 8522254 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.6585. Min Act: -0.1700
Data Index: 445984 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.6585. Min Act: -0.1700
Data Index: 6622020 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.5960. Min Act: -0.1700
Data Index: 8827095 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.5647. Min Act: -0.1700
Data Index: 445536 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.5335. Min Act: -0.1700
Data Index: 7066797 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.5335. Min Act: -0.1700
Data Index: 6565031 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.5022. Min Act: -0.1700
Data Index: 4694100 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.5022. Min Act: -0.1700
Data Index: 771870 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.5022. Min Act: -0.1700
Data Index: 290829 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.4710. Min Act: -0.1700
Data Index: 3075905 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.5022. Min Act: -0.1700
Data Index: 4387820 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.5022. Min Act: -0.1700
Data Index: 8046558 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.4710. Min Act: -0.1700
Data Index: 764933 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.4397. Min Act: -0.1700
Data Index: 4397060 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.4397. Min Act: -0.1700
Data Index: 2410061 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0647. Min Range: -7.0647
Max Act: 6.4397. Min Act: -0.1700
Data Index: 7509983 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19