Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 676 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5116. Min Range: -8.5116
Max Act: 8.5116. Min Act: -0.1700
Data Index: 7140086 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5116. Min Range: -8.5116
Max Act: 8.1991. Min Act: -0.1700
Data Index: 3978671 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5116. Min Range: -8.5116
Max Act: 8.1366. Min Act: -0.1700
Data Index: 4208457 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5116. Min Range: -8.5116
Max Act: 8.0741. Min Act: -0.1700
Data Index: 7109844 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5116. Min Range: -8.5116
Max Act: 8.0741. Min Act: -0.1700
Data Index: 746891 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.9491. Min Act: -0.1700
Data Index: 4134848 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.8866. Min Act: -0.1700
Data Index: 1691590 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.8866. Min Act: -0.1700
Data Index: 4206087 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.8866. Min Act: -0.1700
Data Index: 846903 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.7616. Min Act: -0.1700
Data Index: 8271353 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.7928. Min Act: -0.1700
Data Index: 8209309 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.7303. Min Act: -0.1700
Data Index: 7216804 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.7928. Min Act: -0.1700
Data Index: 5525727 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.6678. Min Act: -0.1700
Data Index: 8252692 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.6366. Min Act: -0.1700
Data Index: 8257911 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.5741. Min Act: -0.1700
Data Index: 7817100 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.6678. Min Act: -0.1700
Data Index: 7361411 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.6678. Min Act: -0.1700
Data Index: 2443053 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.5116. Min Act: -0.1700
Data Index: 1870817 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5116. Min Range: -8.5116
Max Act: 7.6366. Min Act: -0.1700
Data Index: 4682911 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19