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

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

Neuron 1852 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: 1.5543. Min Range: -1.5543

Max Act: 1.5543. Min Act: -0.0000

Data Index: 220415 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.3431. Min Act: -0.0000

Data Index: 988088 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.3246. Min Act: -0.0000

Data Index: 887515 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.3982. Min Act: -0.0000

Data Index: 338715 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.2965. Min Act: -0.0000

Data Index: 514055 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.2980. Min Act: -0.0000

Data Index: 211083 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.2582. Min Act: -0.0000

Data Index: 981522 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.2163. Min Act: -0.0000

Data Index: 654194 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.2261. Min Act: -0.0000

Data Index: 903603 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.1426. Min Act: -0.0000

Data Index: 394713 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.2432. Min Act: -0.0000

Data Index: 312122 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.1390. Min Act: -0.0000

Data Index: 377646 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.1516. Min Act: -0.0000

Data Index: 373968 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.1718. Min Act: -0.0000

Data Index: 1259486 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.2184. Min Act: -0.0000

Data Index: 1190850 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1188699 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.1856. Min Act: -0.0000

Data Index: 1184508 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.1768. Min Act: -0.0000

Data Index: 636630 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.0994. Min Act: -0.0000

Data Index: 1169540 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 1.5543. Min Range: -1.5543

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1146100 (C4 (Web Text))

Max Activating Token Index: 943