Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.6539. Min Act: -0.1700
Data Index: 8811870 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.6539. Min Act: -0.1700
Data Index: 243911 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.5914. Min Act: -0.1700
Data Index: 3699140 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.6227. Min Act: -0.1700
Data Index: 5742320 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.5602. Min Act: -0.1700
Data Index: 5476883 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.5914. Min Act: -0.1700
Data Index: 6837048 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.5289. Min Act: -0.1700
Data Index: 8310168 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.5289. Min Act: -0.1700
Data Index: 8295130 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.5289. Min Act: -0.1700
Data Index: 4669281 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.4664. Min Act: -0.1700
Data Index: 1615082 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.4977. Min Act: -0.1700
Data Index: 940092 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.4977. Min Act: -0.1700
Data Index: 916520 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.4352. Min Act: -0.1700
Data Index: 8707927 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.4039. Min Act: -0.1700
Data Index: 5565582 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.4352. Min Act: -0.1700
Data Index: 6805439 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.4039. Min Act: -0.1700
Data Index: 4417025 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.4352. Min Act: -0.1700
Data Index: 6702952 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.4352. Min Act: -0.1700
Data Index: 2935054 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.4664. Min Act: -0.1700
Data Index: 3619361 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6539. Min Range: -4.6539
Max Act: 4.4352. Min Act: -0.1700
Data Index: 8501408 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19