Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1035 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0531. Min Range: -6.0531
Max Act: 6.0531. Min Act: -0.1700
Data Index: 8682379 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0531. Min Range: -6.0531
Max Act: 6.0219. Min Act: -0.1700
Data Index: 8606928 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.9594. Min Act: -0.1700
Data Index: 5436839 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.8969. Min Act: -0.1700
Data Index: 5478014 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.8344. Min Act: -0.1700
Data Index: 5299611 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.7094. Min Act: -0.1700
Data Index: 2740644 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.7094. Min Act: -0.1700
Data Index: 1699267 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.6156. Min Act: -0.1700
Data Index: 8701114 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.5844. Min Act: -0.1700
Data Index: 403285 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.5531. Min Act: -0.1700
Data Index: 2740645 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.5844. Min Act: -0.1700
Data Index: 3982336 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.5219. Min Act: -0.1700
Data Index: 8517412 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.5219. Min Act: -0.1700
Data Index: 6501179 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.5219. Min Act: -0.1700
Data Index: 3664114 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.4906. Min Act: -0.1700
Data Index: 1500908 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.4594. Min Act: -0.1700
Data Index: 5478013 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.5219. Min Act: -0.1700
Data Index: 2629469 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.5219. Min Act: -0.1700
Data Index: 1390827 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.4906. Min Act: -0.1700
Data Index: 8586207 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0531. Min Range: -6.0531
Max Act: 5.5219. Min Act: -0.1700
Data Index: 7591322 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19