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

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

Neuron 4462 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.8749. Min Act: -0.0000

Data Index: 678009 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.7231. Min Act: -0.0000

Data Index: 1236285 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.5144. Min Act: -0.0000

Data Index: 972026 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.5348. Min Act: -0.0000

Data Index: 751686 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.1332. Min Act: -0.0000

Data Index: 136414 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.2209. Min Act: -0.0000

Data Index: 702537 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.1759. Min Act: -0.0000

Data Index: 1298319 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.8420. Min Act: -0.0000

Data Index: 228070 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.0453. Min Act: -0.0000

Data Index: 436832 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.6368. Min Act: -0.0000

Data Index: 388151 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.7464. Min Act: -0.0000

Data Index: 1172773 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.7670. Min Act: -0.0000

Data Index: 1315680 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.6578. Min Act: -0.0000

Data Index: 923961 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.6759. Min Act: -0.0000

Data Index: 751854 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.7385. Min Act: -0.0000

Data Index: 951956 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.5411. Min Act: -0.0000

Data Index: 1320400 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.5257. Min Act: -0.0000

Data Index: 240628 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.8932. Min Act: -0.0000

Data Index: 332230 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.5440. Min Act: -0.0000

Data Index: 769692 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.7359. Min Act: -0.0000

Data Index: 26467 (C4 (Web Text))

Max Activating Token Index: 459