Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5975 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0384. Min Act: -0.0001

Data Index: 889496 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0382. Min Act: -0.0001

Data Index: 410626 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1297248 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0388. Min Act: -0.0001

Data Index: 1115730 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0357. Min Act: -0.0001

Data Index: 190578 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0400. Min Act: -0.0001

Data Index: 803073 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0369. Min Act: -0.0001

Data Index: 770999 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0365. Min Act: -0.0001

Data Index: 6886 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1160853 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0364. Min Act: -0.0001

Data Index: 559874 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1304629 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1468745 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1316510 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0364. Min Act: -0.0001

Data Index: 700035 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0355. Min Act: -0.0001

Data Index: 712989 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1171955 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1288361 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0323. Min Act: -0.0001

Data Index: 183399 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0358. Min Act: -0.0001

Data Index: 1227512 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0325. Min Act: -0.0001

Data Index: 307045 (C4 (Web Text))

Max Activating Token Index: 800