Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.9186. Min Act: -0.1700
Data Index: 1871942 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.8561. Min Act: -0.1700
Data Index: 7461741 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.7936. Min Act: -0.1700
Data Index: 4927240 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.6998. Min Act: -0.1700
Data Index: 7576870 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.6998. Min Act: -0.1700
Data Index: 3349018 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.6686. Min Act: -0.1700
Data Index: 1961695 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.6686. Min Act: -0.1700
Data Index: 6175890 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.6061. Min Act: -0.1700
Data Index: 1023706 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.6061. Min Act: -0.1700
Data Index: 5839238 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.5748. Min Act: -0.1700
Data Index: 4847876 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.5748. Min Act: -0.1700
Data Index: 1708895 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.5748. Min Act: -0.1700
Data Index: 1887504 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.5748. Min Act: -0.1700
Data Index: 5382153 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.5748. Min Act: -0.1700
Data Index: 115692 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.5748. Min Act: -0.1700
Data Index: 7925197 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.5436. Min Act: -0.1700
Data Index: 2876266 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.5436. Min Act: -0.1700
Data Index: 1151981 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.5436. Min Act: -0.1700
Data Index: 7515297 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.5123. Min Act: -0.1700
Data Index: 4502717 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9186. Min Range: -6.9186
Max Act: 6.5436. Min Act: -0.1700
Data Index: 1151979 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19