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

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

Neuron 2922 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3522. Min Act: -0.0000

Data Index: 899029 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1023483 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1332285 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2595. Min Act: -0.0000

Data Index: 807577 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1296924 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2408. Min Act: -0.0000

Data Index: 296610 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2566. Min Act: -0.0000

Data Index: 252654 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1129385 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2410. Min Act: 0.0000

Data Index: 436248 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2312. Min Act: -0.0000

Data Index: 689657 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2376. Min Act: 0.0000

Data Index: 963766 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2284. Min Act: -0.0000

Data Index: 900167 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2324. Min Act: 0.0000

Data Index: 203108 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2295. Min Act: -0.0000

Data Index: 721843 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2200. Min Act: -0.0000

Data Index: 763731 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1005517 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2241. Min Act: 0.0000

Data Index: 1063105 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2203. Min Act: -0.0000

Data Index: 15516 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2091. Min Act: -0.0000

Data Index: 945893 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.1949. Min Act: 0.0000

Data Index: 764609 (C4 (Web Text))

Max Activating Token Index: 79