Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4330 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0727. Min Range: -6.0727
Max Act: 6.0727. Min Act: -0.1700
Data Index: 2048968 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0727. Min Range: -6.0727
Max Act: 6.0727. Min Act: -0.1700
Data Index: 7331904 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.9790. Min Act: -0.1700
Data Index: 3394877 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.9165. Min Act: -0.1700
Data Index: 4503779 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.8852. Min Act: -0.1700
Data Index: 3703021 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.8540. Min Act: -0.1700
Data Index: 8426224 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.8540. Min Act: -0.1700
Data Index: 3338257 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.8540. Min Act: -0.1700
Data Index: 7666595 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.8227. Min Act: -0.1700
Data Index: 420403 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.8540. Min Act: -0.1700
Data Index: 2541257 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.7602. Min Act: -0.1700
Data Index: 1892622 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.7915. Min Act: -0.1700
Data Index: 3186502 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.7915. Min Act: -0.1700
Data Index: 997828 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.7915. Min Act: -0.1700
Data Index: 2655556 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.7602. Min Act: -0.1700
Data Index: 4752687 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.7602. Min Act: -0.1700
Data Index: 7711161 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.7602. Min Act: -0.1700
Data Index: 4736961 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.7602. Min Act: -0.1700
Data Index: 5602221 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6597293 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0727. Min Range: -6.0727
Max Act: 5.7602. Min Act: -0.1700
Data Index: 5664453 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19