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

Dataset: The Pile

Neuron 5048 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3246. Min Act: -0.0000

Data Index: 206499 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1470480 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1538474 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2937. Min Act: -0.0000

Data Index: 500787 (The Pile)

Max Activating Token Index: 440

Text #4

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2825. Min Act: -0.0000

Data Index: 373126 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2762. Min Act: -0.0000

Data Index: 328000 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1145311 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2560. Min Act: -0.0000

Data Index: 685092 (The Pile)

Max Activating Token Index: 942

Text #8

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2645. Min Act: -0.0000

Data Index: 37124 (The Pile)

Max Activating Token Index: 308

Text #9

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2610. Min Act: 0.0000

Data Index: 1960174 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1120709 (The Pile)

Max Activating Token Index: 60

Text #11

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2569. Min Act: -0.0000

Data Index: 225472 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1098358 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2487. Min Act: 0.0000

Data Index: 117158 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2535. Min Act: -0.0000

Data Index: 543079 (The Pile)

Max Activating Token Index: 95

Text #15

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2527. Min Act: -0.0000

Data Index: 88039 (The Pile)

Max Activating Token Index: 106

Text #16

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2534. Min Act: -0.0000

Data Index: 446073 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2524. Min Act: -0.0000

Data Index: 781495 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2500. Min Act: 0.0000

Data Index: 1144596 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2509. Min Act: 0.0000

Data Index: 1464276 (The Pile)

Max Activating Token Index: 193