Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2408 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3878. Min Act: -0.1700
Data Index: 291481 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3878. Min Act: -0.1700
Data Index: 8271432 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3565. Min Act: -0.1700
Data Index: 6347500 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3565. Min Act: -0.1700
Data Index: 4858850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3565. Min Act: -0.1700
Data Index: 1177821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3565. Min Act: -0.1700
Data Index: 2015106 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3565. Min Act: -0.1700
Data Index: 3501216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3253. Min Act: -0.1700
Data Index: 1804964 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3253. Min Act: -0.1700
Data Index: 3684471 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3253. Min Act: -0.1700
Data Index: 3951854 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3253. Min Act: -0.1700
Data Index: 8231837 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3253. Min Act: -0.1700
Data Index: 7177635 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3253. Min Act: -0.1700
Data Index: 2041920 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3253. Min Act: -0.1700
Data Index: 4623354 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3253. Min Act: -0.1700
Data Index: 6884473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3253. Min Act: -0.1700
Data Index: 8491464 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3253. Min Act: -0.1700
Data Index: 6110977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.3253. Min Act: -0.1700
Data Index: 6320833 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.2940. Min Act: -0.1700
Data Index: 2343344 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3878. Min Range: -4.3878
Max Act: 4.2940. Min Act: -0.1700
Data Index: 1603539 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19