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

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

Neuron 1200 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: 0.0318. Min Range: -0.0318

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1635733 (Python Code)

Max Activating Token Index: 449

Text #1

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0318. Min Act: -0.0003

Data Index: 826455 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1417475 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1408935 (Python Code)

Max Activating Token Index: 310

Text #4

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1623856 (Python Code)

Max Activating Token Index: 454

Text #5

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0275. Min Act: -0.0003

Data Index: 255424 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0287. Min Act: -0.0003

Data Index: 43121 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1535218 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0280. Min Act: -0.0003

Data Index: 421117 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0278. Min Act: -0.0003

Data Index: 807177 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0276. Min Act: -0.0003

Data Index: 439424 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0264. Min Act: -0.0003

Data Index: 378357 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1448463 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0263. Min Act: -0.0003

Data Index: 670628 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0250. Min Act: -0.0003

Data Index: 649313 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0270. Min Act: -0.0003

Data Index: 346922 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0256. Min Act: -0.0003

Data Index: 157363 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1550014 (Python Code)

Max Activating Token Index: 535

Text #18

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1501300 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1467952 (Python Code)

Max Activating Token Index: 2