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

Dataset: The Pile

Neuron 3198 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.8318. Min Act: -0.0000

Data Index: 227173 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7361. Min Act: -0.0000

Data Index: 508186 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.6393. Min Act: -0.0000

Data Index: 1598621 (The Pile)

Max Activating Token Index: 864

Text #3

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7085. Min Act: -0.0000

Data Index: 1150249 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4993. Min Act: -0.0000

Data Index: 1454346 (The Pile)

Max Activating Token Index: 72

Text #5

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1423935 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4291. Min Act: -0.0000

Data Index: 383413 (The Pile)

Max Activating Token Index: 724

Text #7

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4564. Min Act: -0.0000

Data Index: 887603 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4214. Min Act: -0.0000

Data Index: 1926440 (The Pile)

Max Activating Token Index: 792

Text #9

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3247. Min Act: -0.0000

Data Index: 1637199 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.2393. Min Act: -0.0000

Data Index: 705296 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.2585. Min Act: -0.0000

Data Index: 889926 (The Pile)

Max Activating Token Index: 842

Text #12

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3373. Min Act: -0.0000

Data Index: 980226 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3155. Min Act: -0.0000

Data Index: 712142 (The Pile)

Max Activating Token Index: 969

Text #14

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.1854. Min Act: -0.0000

Data Index: 538798 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.2002. Min Act: -0.0000

Data Index: 434274 (The Pile)

Max Activating Token Index: 957

Text #16

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.2504. Min Act: -0.0000

Data Index: 640450 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.2068. Min Act: -0.0000

Data Index: 1732456 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.2663. Min Act: -0.0000

Data Index: 142433 (The Pile)

Max Activating Token Index: 731

Text #19

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1267189 (The Pile)

Max Activating Token Index: 770