Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2019 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0336. Min Act: -0.0006

Data Index: 1445870 (Python Code)

Max Activating Token Index: 499

Text #1

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1390471 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0308. Min Act: -0.0006

Data Index: 1650597 (Python Code)

Max Activating Token Index: 56

Text #3

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0302. Min Act: -0.0006

Data Index: 1450851 (Python Code)

Max Activating Token Index: 114

Text #4

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1441785 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1610440 (Python Code)

Max Activating Token Index: 381

Text #6

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1540841 (Python Code)

Max Activating Token Index: 658

Text #7

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0291. Min Act: -0.0006

Data Index: 1644110 (Python Code)

Max Activating Token Index: 587

Text #8

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1620843 (Python Code)

Max Activating Token Index: 644

Text #9

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0297. Min Act: -0.0006

Data Index: 1428848 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1638053 (Python Code)

Max Activating Token Index: 615

Text #11

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1509676 (Python Code)

Max Activating Token Index: 156

Text #12

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1384591 (Python Code)

Max Activating Token Index: 428

Text #13

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1361256 (Python Code)

Max Activating Token Index: 237

Text #14

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1366914 (Python Code)

Max Activating Token Index: 471

Text #15

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1467676 (Python Code)

Max Activating Token Index: 497

Text #16

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1463745 (Python Code)

Max Activating Token Index: 757

Text #17

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1375035 (Python Code)

Max Activating Token Index: 349

Text #18

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1656498 (Python Code)

Max Activating Token Index: 177

Text #19

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1614074 (Python Code)

Max Activating Token Index: 26