Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4203 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.5329. Min Act: -0.0001

Data Index: 1029922 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4939. Min Act: -0.0001

Data Index: 493485 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4579. Min Act: -0.0001

Data Index: 346876 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4463. Min Act: -0.0001

Data Index: 154457 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4158. Min Act: -0.0001

Data Index: 779530 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4157. Min Act: -0.0001

Data Index: 324126 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3969. Min Act: -0.0001

Data Index: 693890 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4240. Min Act: -0.0001

Data Index: 1178483 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4043. Min Act: -0.0001

Data Index: 108207 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4173. Min Act: -0.0001

Data Index: 1237420 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3986. Min Act: -0.0001

Data Index: 272898 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4084. Min Act: -0.0001

Data Index: 578195 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4150. Min Act: -0.0001

Data Index: 609140 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4278. Min Act: -0.0001

Data Index: 1350695 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4258. Min Act: -0.0001

Data Index: 721008 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3771. Min Act: -0.0001

Data Index: 1295115 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4170. Min Act: -0.0001

Data Index: 861972 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4007. Min Act: -0.0001

Data Index: 438627 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1110320 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3954. Min Act: -0.0001

Data Index: 295599 (C4 (Web Text))

Max Activating Token Index: 449