Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2222 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0387. Min Act: -0.0004

Data Index: 1526953 (Python Code)

Max Activating Token Index: 603

Text #1

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0369. Min Act: -0.0004

Data Index: 692396 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0388. Min Act: -0.0004

Data Index: 1337520 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0348. Min Act: -0.0004

Data Index: 1056848 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0344. Min Act: -0.0004

Data Index: 395902 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0332. Min Act: -0.0004

Data Index: 322478 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0318. Min Act: -0.0004

Data Index: 790654 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0315. Min Act: -0.0004

Data Index: 1145251 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0314. Min Act: -0.0004

Data Index: 390345 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0287. Min Act: -0.0004

Data Index: 204331 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0287. Min Act: -0.0004

Data Index: 1299238 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0279. Min Act: -0.0004

Data Index: 685211 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0308. Min Act: -0.0004

Data Index: 1212694 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0281. Min Act: -0.0004

Data Index: 637957 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0308. Min Act: -0.0004

Data Index: 475291 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0291. Min Act: -0.0004

Data Index: 8401 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0308. Min Act: -0.0004

Data Index: 992308 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0295. Min Act: -0.0004

Data Index: 904843 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0318. Min Act: -0.0004

Data Index: 1367320 (Python Code)

Max Activating Token Index: 798

Text #19

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0304. Min Act: -0.0004

Data Index: 142890 (C4 (Web Text))

Max Activating Token Index: 62