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

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

Neuron 576 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: 0.3195. Min Range: -0.3195

Max Act: 0.3195. Min Act: -0.0001

Data Index: 979014 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2318. Min Act: -0.0001

Data Index: 666874 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2336. Min Act: -0.0001

Data Index: 929600 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2389. Min Act: -0.0001

Data Index: 171026 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2280. Min Act: -0.0001

Data Index: 566333 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2360. Min Act: -0.0001

Data Index: 1158924 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2209. Min Act: -0.0001

Data Index: 5187 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1322311 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2123. Min Act: -0.0001

Data Index: 229217 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2000. Min Act: -0.0001

Data Index: 559647 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2275. Min Act: -0.0001

Data Index: 84490 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2269. Min Act: -0.0001

Data Index: 1323756 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2237. Min Act: -0.0001

Data Index: 259036 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2381. Min Act: -0.0001

Data Index: 40177 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2297. Min Act: -0.0001

Data Index: 526028 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2145. Min Act: -0.0001

Data Index: 756116 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2060. Min Act: -0.0001

Data Index: 934395 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2286. Min Act: -0.0001

Data Index: 559144 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2087. Min Act: -0.0001

Data Index: 572248 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1975. Min Act: -0.0001

Data Index: 358450 (C4 (Web Text))

Max Activating Token Index: 652