Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3590 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.2964. Min Range: -3.2964
Max Act: 3.1265. Min Act: -0.0001
Data Index: 341271 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2964. Min Range: -3.2964
Max Act: 3.2964. Min Act: -0.0001
Data Index: 221655 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.8360. Min Act: -0.0001
Data Index: 1193811 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.4490. Min Act: -0.0001
Data Index: 497392 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.2094. Min Act: -0.0001
Data Index: 704765 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.5000. Min Act: -0.0001
Data Index: 1079590 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.3418. Min Act: -0.0001
Data Index: 403330 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.2868. Min Act: -0.0001
Data Index: 202335 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.3647. Min Act: -0.0001
Data Index: 98837 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.3623. Min Act: -0.0001
Data Index: 845298 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.4344. Min Act: -0.0001
Data Index: 327688 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.3191. Min Act: -0.0001
Data Index: 720647 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.2964. Min Act: -0.0001
Data Index: 855387 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.3084. Min Act: -0.0001
Data Index: 1336721 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.1934. Min Act: -0.0001
Data Index: 1124723 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.3934. Min Act: -0.0001
Data Index: 1193468 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.0453. Min Act: -0.0001
Data Index: 1180811 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.2634. Min Act: -0.0001
Data Index: 659774 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.0234. Min Act: -0.0001
Data Index: 450124 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2964. Min Range: -3.2964
Max Act: 2.1116. Min Act: -0.0001
Data Index: 634471 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19