Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0993. Min Range: -5.0993
Max Act: 5.0993. Min Act: -0.1700
Data Index: 227453 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0993. Min Range: -5.0993
Max Act: 5.0368. Min Act: -0.1700
Data Index: 8167498 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0993. Min Range: -5.0993
Max Act: 5.0055. Min Act: -0.1700
Data Index: 1641443 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.9743. Min Act: -0.1700
Data Index: 2989812 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0993. Min Range: -5.0993
Max Act: 5.0055. Min Act: -0.1700
Data Index: 6709539 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.9430. Min Act: -0.1700
Data Index: 7551615 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.9118. Min Act: -0.1700
Data Index: 5822445 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.9430. Min Act: -0.1700
Data Index: 7200285 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.9430. Min Act: -0.1700
Data Index: 3437911 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.9743. Min Act: -0.1700
Data Index: 860686 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.8805. Min Act: -0.1700
Data Index: 8388448 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.9118. Min Act: -0.1700
Data Index: 3608974 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.9430. Min Act: -0.1700
Data Index: 8148594 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.8805. Min Act: -0.1700
Data Index: 1050170 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.8805. Min Act: -0.1700
Data Index: 5085888 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.8805. Min Act: -0.1700
Data Index: 5472706 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.8805. Min Act: -0.1700
Data Index: 7636313 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.8805. Min Act: -0.1700
Data Index: 397878 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.8805. Min Act: -0.1700
Data Index: 2576028 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0993. Min Range: -5.0993
Max Act: 4.8805. Min Act: -0.1700
Data Index: 473804 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19