Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 49 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1073051 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0278. Min Act: -0.0003

Data Index: 908264 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0265. Min Act: -0.0003

Data Index: 388140 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0271. Min Act: -0.0003

Data Index: 833995 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0236. Min Act: -0.0003

Data Index: 18776 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0259. Min Act: -0.0003

Data Index: 957914 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0261. Min Act: -0.0003

Data Index: 178095 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1076312 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0250. Min Act: -0.0003

Data Index: 531112 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0260. Min Act: -0.0003

Data Index: 982975 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0243. Min Act: -0.0003

Data Index: 55417 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0248. Min Act: -0.0003

Data Index: 410527 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0256. Min Act: -0.0003

Data Index: 744385 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0217. Min Act: -0.0003

Data Index: 749494 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0249. Min Act: -0.0003

Data Index: 499562 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1648063 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1098810 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1317288 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0223. Min Act: -0.0003

Data Index: 651772 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0239. Min Act: -0.0003

Data Index: 472506 (C4 (Web Text))

Max Activating Token Index: 478