Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4761 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.7504. Min Act: -0.1700
Data Index: 146982 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.7191. Min Act: -0.1700
Data Index: 6143375 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.7035. Min Act: -0.1700
Data Index: 1854069 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.6878. Min Act: -0.1700
Data Index: 1862240 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.6722. Min Act: -0.1700
Data Index: 4771917 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.6722. Min Act: -0.1700
Data Index: 1924338 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.6252. Min Act: -0.1700
Data Index: 4428924 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.6409. Min Act: -0.1700
Data Index: 1054260 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.6252. Min Act: -0.1700
Data Index: 8578903 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.6252. Min Act: -0.1700
Data Index: 2027320 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.6252. Min Act: -0.1700
Data Index: 643783 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.5939. Min Act: -0.1700
Data Index: 2330358 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.5783. Min Act: -0.1700
Data Index: 6560282 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.5783. Min Act: -0.1700
Data Index: 7868581 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.5939. Min Act: -0.1700
Data Index: 749972 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.5939. Min Act: -0.1700
Data Index: 13587 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.5783. Min Act: -0.1700
Data Index: 8287941 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.5626. Min Act: -0.1700
Data Index: 8547576 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.5313. Min Act: -0.1700
Data Index: 5467864 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7504. Min Range: -3.7504
Max Act: 3.5313. Min Act: -0.1700
Data Index: 589357 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19