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

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

Neuron 2431 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0002

Data Index: 996915 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0430. Min Act: -0.0002

Data Index: 189318 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0429. Min Act: -0.0002

Data Index: 933704 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0398. Min Act: -0.0002

Data Index: 360375 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0421. Min Act: -0.0002

Data Index: 440895 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1239882 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1089122 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1312461 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0386. Min Act: -0.0002

Data Index: 151422 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0445. Min Act: -0.0002

Data Index: 106278 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0396. Min Act: -0.0002

Data Index: 910601 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1355582 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0382. Min Act: -0.0002

Data Index: 264034 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0426. Min Act: -0.0001

Data Index: 17907 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1234592 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0412. Min Act: -0.0002

Data Index: 476236 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1352502 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0402. Min Act: -0.0002

Data Index: 957727 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1406777 (Python Code)

Max Activating Token Index: 316

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0350. Min Act: -0.0001

Data Index: 971878 (C4 (Web Text))

Max Activating Token Index: 322