Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2290. Min Range: -8.2290
Max Act: 8.1665. Min Act: -0.1700
Data Index: 4440785 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2290. Min Range: -8.2290
Max Act: 8.2290. Min Act: -0.1700
Data Index: 7220251 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2290. Min Range: -8.2290
Max Act: 8.2290. Min Act: -0.1700
Data Index: 2341447 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2290. Min Range: -8.2290
Max Act: 8.2290. Min Act: -0.1700
Data Index: 2027986 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2290. Min Range: -8.2290
Max Act: 8.0415. Min Act: -0.1700
Data Index: 2785625 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.9165. Min Act: -0.1700
Data Index: 6127859 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.9165. Min Act: -0.1700
Data Index: 4440788 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.9165. Min Act: -0.1700
Data Index: 7756429 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.8852. Min Act: -0.1700
Data Index: 6199186 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.8852. Min Act: -0.1700
Data Index: 1151750 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.8540. Min Act: -0.1700
Data Index: 5659502 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.8227. Min Act: -0.1700
Data Index: 7777587 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.8540. Min Act: -0.1700
Data Index: 4588704 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.7915. Min Act: -0.1700
Data Index: 4931945 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.6665. Min Act: -0.1700
Data Index: 7391858 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.6665. Min Act: -0.1700
Data Index: 3670279 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.6977. Min Act: -0.1700
Data Index: 164669 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.7290. Min Act: -0.1700
Data Index: 6916908 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.6040. Min Act: -0.1700
Data Index: 876434 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2290. Min Range: -8.2290
Max Act: 7.6352. Min Act: -0.1700
Data Index: 2336690 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19