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

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

Neuron 1930 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.3681. Min Act: -0.0000

Data Index: 1078728 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.2562. Min Act: -0.0000

Data Index: 372491 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.3668. Min Act: -0.0000

Data Index: 595919 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.2370. Min Act: -0.0000

Data Index: 1175318 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.4328. Min Act: -0.0000

Data Index: 555424 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.2936. Min Act: -0.0001

Data Index: 316947 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.2296. Min Act: -0.0000

Data Index: 946429 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.2236. Min Act: -0.0000

Data Index: 891057 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.2098. Min Act: -0.0001

Data Index: 248621 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.3240. Min Act: -0.0000

Data Index: 525214 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.1950. Min Act: -0.0000

Data Index: 976072 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.0850. Min Act: -0.0000

Data Index: 955009 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.1775. Min Act: -0.0000

Data Index: 91125 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.1835. Min Act: -0.0001

Data Index: 1188464 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.0545. Min Act: -0.0000

Data Index: 1319577 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.0354. Min Act: -0.0000

Data Index: 311523 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.2470. Min Act: -0.0000

Data Index: 1300616 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.1099. Min Act: -0.0000

Data Index: 426163 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.1183. Min Act: -0.0001

Data Index: 542227 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 2.4328. Min Range: -2.4328

Max Act: 2.1103. Min Act: -0.0001

Data Index: 406990 (C4 (Web Text))

Max Activating Token Index: 698