Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1221. Min Range: -9.1221
Max Act: 9.1221. Min Act: -0.1700
Data Index: 8092704 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1221. Min Range: -9.1221
Max Act: 8.6221. Min Act: -0.1700
Data Index: 2107631 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1221. Min Range: -9.1221
Max Act: 8.6846. Min Act: -0.1700
Data Index: 5401027 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1221. Min Range: -9.1221
Max Act: 8.3096. Min Act: -0.1700
Data Index: 6082216 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1221. Min Range: -9.1221
Max Act: 8.1221. Min Act: -0.1700
Data Index: 5179994 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.5283. Min Act: -0.1700
Data Index: 4631522 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.4971. Min Act: -0.1700
Data Index: 7894493 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1221. Min Range: -9.1221
Max Act: 8.3721. Min Act: -0.1700
Data Index: 3918523 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.9971. Min Act: -0.1700
Data Index: 2116130 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1221. Min Range: -9.1221
Max Act: 8.8721. Min Act: -0.1700
Data Index: 3918529 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.7783. Min Act: -0.1700
Data Index: 5161479 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.5908. Min Act: -0.1700
Data Index: 111202 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.7471. Min Act: -0.1700
Data Index: 8068068 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.7783. Min Act: -0.1700
Data Index: 1457949 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.9033. Min Act: -0.1700
Data Index: 227757 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.7471. Min Act: -0.1700
Data Index: 6739162 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.8096. Min Act: -0.1700
Data Index: 6668915 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.7158. Min Act: -0.1700
Data Index: 2016337 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.7158. Min Act: -0.1700
Data Index: 624919 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1221. Min Range: -9.1221
Max Act: 7.7471. Min Act: -0.1700
Data Index: 443124 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19