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

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

Neuron 1038 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: 0.0400. Min Range: -0.0400

Max Act: 0.0400. Min Act: -0.0003

Data Index: 186032 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1606751 (Python Code)

Max Activating Token Index: 261

Text #2

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1579943 (Python Code)

Max Activating Token Index: 431

Text #3

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1411639 (Python Code)

Max Activating Token Index: 690

Text #4

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1546688 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0357. Min Act: -0.0003

Data Index: 950150 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1144522 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0355. Min Act: -0.0003

Data Index: 623684 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1180243 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1541933 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0336. Min Act: -0.0003

Data Index: 744616 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1069531 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1361244 (Python Code)

Max Activating Token Index: 705

Text #13

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0344. Min Act: -0.0003

Data Index: 993977 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1645268 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0352. Min Act: -0.0003

Data Index: 927005 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1280570 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0344. Min Act: -0.0003

Data Index: 150088 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0348. Min Act: -0.0003

Data Index: 1605332 (Python Code)

Max Activating Token Index: 473

Text #19

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1061005 (C4 (Web Text))

Max Activating Token Index: 1023