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

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

Neuron 2955 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.6212. Min Act: -0.0001

Data Index: 490468 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5624. Min Act: -0.0001

Data Index: 498275 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4950. Min Act: -0.0001

Data Index: 524407 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4496. Min Act: -0.0001

Data Index: 630021 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4254. Min Act: -0.0001

Data Index: 1087980 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4279. Min Act: -0.0001

Data Index: 250036 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4068. Min Act: -0.0001

Data Index: 1107089 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3977. Min Act: -0.0001

Data Index: 637544 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3741. Min Act: -0.0001

Data Index: 972616 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3555. Min Act: -0.0001

Data Index: 925497 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3815. Min Act: -0.0001

Data Index: 322108 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3751. Min Act: -0.0001

Data Index: 811884 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3297. Min Act: -0.0001

Data Index: 790229 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3751. Min Act: -0.0001

Data Index: 673417 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3706. Min Act: -0.0001

Data Index: 9109 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3481. Min Act: -0.0001

Data Index: 409217 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3237. Min Act: -0.0001

Data Index: 241061 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3551. Min Act: -0.0001

Data Index: 429577 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3613. Min Act: -0.0001

Data Index: 706401 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3469. Min Act: -0.0001

Data Index: 55106 (C4 (Web Text))

Max Activating Token Index: 392