Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2079 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.8123. Min Act: -0.1700
Data Index: 3605440 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6914. Min Act: -0.1700
Data Index: 2664105 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6740. Min Act: -0.1700
Data Index: 5161276 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6740. Min Act: -0.1700
Data Index: 237276 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6740. Min Act: -0.1700
Data Index: 1880344 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6566. Min Act: -0.1685
Data Index: 8767319 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6566. Min Act: -0.1700
Data Index: 6427150 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6653. Min Act: -0.1700
Data Index: 7619700 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6566. Min Act: -0.1700
Data Index: 5875398 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6566. Min Act: -0.1700
Data Index: 1834436 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6479. Min Act: -0.1696
Data Index: 2933259 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6392. Min Act: -0.1700
Data Index: 2932741 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6305. Min Act: -0.1700
Data Index: 7786720 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6392. Min Act: -0.1700
Data Index: 8620931 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6305. Min Act: -0.1699
Data Index: 2138371 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6305. Min Act: -0.1700
Data Index: 1997059 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6392. Min Act: -0.1700
Data Index: 5301986 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6305. Min Act: -0.1694
Data Index: 4048220 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6305. Min Act: -0.1698
Data Index: 1956223 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8123. Min Range: -1.8123
Max Act: 1.6392. Min Act: -0.1700
Data Index: 2217909 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19