Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1515 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2039. Min Range: -6.2039
Max Act: 6.2039. Min Act: -0.1700
Data Index: 2814 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2039. Min Range: -6.2039
Max Act: 6.1727. Min Act: -0.1700
Data Index: 7301892 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2039. Min Range: -6.2039
Max Act: 6.1102. Min Act: -0.1700
Data Index: 4464556 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2039. Min Range: -6.2039
Max Act: 6.0789. Min Act: -0.1700
Data Index: 2504326 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.9852. Min Act: -0.1700
Data Index: 1731917 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.9852. Min Act: -0.1700
Data Index: 4940924 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.9852. Min Act: -0.1700
Data Index: 796226 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.9539. Min Act: -0.1700
Data Index: 6638490 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.9227. Min Act: -0.1700
Data Index: 984264 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.8914. Min Act: -0.1700
Data Index: 3229023 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.7977. Min Act: -0.1700
Data Index: 4184807 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.8289. Min Act: -0.1700
Data Index: 7728514 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.8289. Min Act: -0.1700
Data Index: 2795329 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.7977. Min Act: -0.1700
Data Index: 6673827 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.7039. Min Act: -0.1700
Data Index: 8366503 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.7664. Min Act: -0.1700
Data Index: 8357860 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.7664. Min Act: -0.1700
Data Index: 7964748 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.7352. Min Act: -0.1700
Data Index: 3856081 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.7664. Min Act: -0.1700
Data Index: 7602246 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2039. Min Range: -6.2039
Max Act: 5.7664. Min Act: -0.1700
Data Index: 1262314 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19