Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.2456. Min Act: -0.1700
Data Index: 1896161 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.2768. Min Act: -0.1700
Data Index: 5140833 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.2143. Min Act: -0.1700
Data Index: 7656728 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1831. Min Act: -0.1700
Data Index: 7354367 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.2143. Min Act: -0.1700
Data Index: 4453423 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.2143. Min Act: -0.1700
Data Index: 5316259 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.2143. Min Act: -0.1700
Data Index: 1200955 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1831. Min Act: -0.1700
Data Index: 1701238 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1831. Min Act: -0.1700
Data Index: 7916893 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1831. Min Act: -0.1700
Data Index: 6991859 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1831. Min Act: -0.1700
Data Index: 6856577 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1831. Min Act: -0.1700
Data Index: 1280980 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1831. Min Act: -0.1700
Data Index: 4291655 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1831. Min Act: -0.1700
Data Index: 4726433 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1831. Min Act: -0.1700
Data Index: 4589035 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1831. Min Act: -0.1700
Data Index: 2236944 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1518. Min Act: -0.1700
Data Index: 2841814 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1206. Min Act: -0.1700
Data Index: 995201 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1518. Min Act: -0.1700
Data Index: 3204736 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2768. Min Range: -6.2768
Max Act: 6.1518. Min Act: -0.1700
Data Index: 3076483 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19