Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3691 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.9166. Min Act: -0.0001
Data Index: 718611 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.9206. Min Act: -0.0001
Data Index: 914415 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.9149. Min Act: -0.0001
Data Index: 1228292 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.9178. Min Act: -0.0001
Data Index: 472472 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.8596. Min Act: -0.0001
Data Index: 1031611 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.7921. Min Act: -0.0001
Data Index: 742633 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.6460. Min Act: -0.0001
Data Index: 115101 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.6267. Min Act: -0.0001
Data Index: 719299 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.7279. Min Act: -0.0001
Data Index: 49349 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.7417. Min Act: -0.0001
Data Index: 551162 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.4764. Min Act: -0.0001
Data Index: 1115449 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.5980. Min Act: -0.0001
Data Index: 88910 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.5414. Min Act: -0.0001
Data Index: 724835 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.4072. Min Act: -0.0001
Data Index: 52849 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.5044. Min Act: -0.0001
Data Index: 1310001 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.4738. Min Act: -0.0001
Data Index: 680245 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.4784. Min Act: -0.0001
Data Index: 77539 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.4571. Min Act: -0.0001
Data Index: 80430 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.4454. Min Act: -0.0001
Data Index: 939600 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9206. Min Range: -2.9206
Max Act: 2.4310. Min Act: -0.0001
Data Index: 589492 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19