Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3236 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.9878. Min Act: -0.1698
Data Index: 1790443 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8941. Min Act: -0.1699
Data Index: 1790454 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8628. Min Act: -0.1700
Data Index: 1790496 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8628. Min Act: -0.1700
Data Index: 860493 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8316. Min Act: -0.1700
Data Index: 8338080 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8316. Min Act: -0.1699
Data Index: 3762154 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8316. Min Act: -0.1700
Data Index: 1179683 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8316. Min Act: -0.1699
Data Index: 5472941 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8316. Min Act: -0.1700
Data Index: 2227502 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8316. Min Act: -0.1700
Data Index: 5325293 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8316. Min Act: -0.1700
Data Index: 2355577 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8316. Min Act: -0.1700
Data Index: 8732647 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8316. Min Act: -0.1700
Data Index: 1179720 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8003. Min Act: -0.1700
Data Index: 5472935 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8003. Min Act: -0.1700
Data Index: 6506872 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8003. Min Act: -0.1700
Data Index: 6663571 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8316. Min Act: -0.1700
Data Index: 2355543 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8003. Min Act: -0.1700
Data Index: 6663600 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.7691. Min Act: -0.1700
Data Index: 7364930 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9878. Min Range: -5.9878
Max Act: 5.8003. Min Act: -0.1700
Data Index: 601750 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19