Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.7034. Min Act: -0.1700
Data Index: 1601231 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.6722. Min Act: -0.1700
Data Index: 4394647 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.6409. Min Act: -0.1700
Data Index: 2331114 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.6097. Min Act: -0.1700
Data Index: 7330620 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.6409. Min Act: -0.1700
Data Index: 7336293 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.5784. Min Act: -0.1700
Data Index: 4799503 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.5159. Min Act: -0.1700
Data Index: 4292881 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.4847. Min Act: -0.1700
Data Index: 8343508 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.5159. Min Act: -0.1700
Data Index: 702509 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.5159. Min Act: -0.1700
Data Index: 5031725 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.4847. Min Act: -0.1700
Data Index: 6546489 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.4847. Min Act: -0.1700
Data Index: 1916671 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.5159. Min Act: -0.1700
Data Index: 8345305 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.4847. Min Act: -0.1700
Data Index: 6438763 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.4534. Min Act: -0.1700
Data Index: 2938147 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.4847. Min Act: -0.1700
Data Index: 1134141 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.4847. Min Act: -0.1700
Data Index: 900444 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.4847. Min Act: -0.1700
Data Index: 4288106 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.4534. Min Act: -0.1700
Data Index: 8035690 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7034. Min Range: -5.7034
Max Act: 5.4222. Min Act: -0.1700
Data Index: 8797381 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19