Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 311 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.2091. Min Range: -1.2091
Max Act: 1.2091. Min Act: -0.0001
Data Index: 1122938 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2091. Min Range: -1.2091
Max Act: 1.1541. Min Act: -0.0001
Data Index: 17007 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2091. Min Range: -1.2091
Max Act: 1.1040. Min Act: -0.0001
Data Index: 521533 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2091. Min Range: -1.2091
Max Act: 1.0164. Min Act: -0.0001
Data Index: 1115382 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2091. Min Range: -1.2091
Max Act: 1.0379. Min Act: -0.0001
Data Index: 707169 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.9824. Min Act: -0.0001
Data Index: 1002446 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.9191. Min Act: -0.0001
Data Index: 561899 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.9428. Min Act: -0.0001
Data Index: 1202063 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2091. Min Range: -1.2091
Max Act: 1.0392. Min Act: -0.0001
Data Index: 695984 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.8397. Min Act: -0.0001
Data Index: 479504 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.9317. Min Act: -0.0001
Data Index: 801906 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.9434. Min Act: -0.0001
Data Index: 1211481 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.9077. Min Act: -0.0001
Data Index: 11025 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.9335. Min Act: -0.0001
Data Index: 1281757 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.8821. Min Act: -0.0001
Data Index: 94478 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.9235. Min Act: -0.0001
Data Index: 1011218 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.7625. Min Act: -0.0001
Data Index: 303099 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.8640. Min Act: -0.0001
Data Index: 723654 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.8778. Min Act: -0.0001
Data Index: 71027 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2091. Min Range: -1.2091
Max Act: 0.9280. Min Act: -0.0001
Data Index: 239964 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19