Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4442 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1019696 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.3214. Min Act: -0.0000

Data Index: 163930 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.3362. Min Act: -0.0000

Data Index: 45342 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1273654 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2349. Min Act: -0.0000

Data Index: 361415 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2348. Min Act: -0.0000

Data Index: 656292 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2382. Min Act: -0.0000

Data Index: 666774 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2299. Min Act: -0.0000

Data Index: 114698 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2354. Min Act: -0.0000

Data Index: 399514 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2265. Min Act: -0.0000

Data Index: 551754 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2359. Min Act: -0.0000

Data Index: 512027 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2188. Min Act: -0.0000

Data Index: 238762 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2310. Min Act: -0.0000

Data Index: 227640 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1186472 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2209. Min Act: -0.0000

Data Index: 847866 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.1985. Min Act: -0.0000

Data Index: 477250 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2096. Min Act: -0.0000

Data Index: 469960 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.1979. Min Act: -0.0000

Data Index: 886820 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.1927. Min Act: -0.0000

Data Index: 612786 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2036. Min Act: -0.0000

Data Index: 192950 (C4 (Web Text))

Max Activating Token Index: 23