Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 71 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0261. Min Act: -0.0006

Data Index: 1044302 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0249. Min Act: -0.0006

Data Index: 131630 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0248. Min Act: -0.0006

Data Index: 950126 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1560769 (Python Code)

Max Activating Token Index: 325

Text #4

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1260332 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0240. Min Act: -0.0006

Data Index: 354979 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0234. Min Act: -0.0006

Data Index: 973520 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1116648 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0242. Min Act: -0.0006

Data Index: 113176 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0232. Min Act: -0.0006

Data Index: 135477 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0237. Min Act: -0.0006

Data Index: 686234 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0231. Min Act: -0.0006

Data Index: 184851 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1108375 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1211175 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1520793 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0227. Min Act: -0.0006

Data Index: 607281 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0232. Min Act: -0.0006

Data Index: 145365 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0225. Min Act: -0.0006

Data Index: 626449 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1621130 (Python Code)

Max Activating Token Index: 301

Text #19

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0228. Min Act: -0.0006

Data Index: 752397 (C4 (Web Text))

Max Activating Token Index: 329