Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2725 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2429. Min Range: -2.2429
Max Act: 2.2429. Min Act: -0.0001
Data Index: 403877 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.8367. Min Act: -0.0001
Data Index: 914632 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.8699. Min Act: -0.0001
Data Index: 220778 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.9759. Min Act: -0.0001
Data Index: 1316968 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.7639. Min Act: -0.0001
Data Index: 1627458 (Python Code)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.6616. Min Act: -0.0001
Data Index: 1147647 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.6160. Min Act: -0.0001
Data Index: 1102571 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.7517. Min Act: -0.0001
Data Index: 1153722 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.3280. Min Act: -0.0001
Data Index: 1253825 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.6675. Min Act: -0.0001
Data Index: 230451 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.5860. Min Act: -0.0001
Data Index: 1652701 (Python Code)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.6254. Min Act: -0.0001
Data Index: 1365198 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.6237. Min Act: -0.0001
Data Index: 1194393 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.6005. Min Act: -0.0001
Data Index: 980719 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.6166. Min Act: -0.0001
Data Index: 1652768 (Python Code)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.6381. Min Act: -0.0001
Data Index: 1624040 (Python Code)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.6669. Min Act: -0.0001
Data Index: 1161130 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.6862. Min Act: -0.0001
Data Index: 831530 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.6698. Min Act: -0.0001
Data Index: 1613225 (Python Code)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2429. Min Range: -2.2429
Max Act: 1.5967. Min Act: -0.0001
Data Index: 407003 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19