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

Dataset: The Pile

Neuron 2623 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.7289. Min Act: -0.0000

Data Index: 87792 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6352. Min Act: -0.0000

Data Index: 608018 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6653. Min Act: -0.0000

Data Index: 338058 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1101625 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.4531. Min Act: -0.0000

Data Index: 1128414 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.4262. Min Act: -0.0000

Data Index: 1115073 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.3408. Min Act: -0.0000

Data Index: 610380 (The Pile)

Max Activating Token Index: 738

Text #7

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.4502. Min Act: -0.0000

Data Index: 185803 (The Pile)

Max Activating Token Index: 318

Text #8

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.4000. Min Act: -0.0000

Data Index: 1326958 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.4318. Min Act: -0.0000

Data Index: 1383089 (The Pile)

Max Activating Token Index: 984

Text #10

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.4336. Min Act: -0.0000

Data Index: 1809024 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.3785. Min Act: -0.0000

Data Index: 648165 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.3751. Min Act: -0.0000

Data Index: 459990 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.3781. Min Act: -0.0000

Data Index: 741116 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.3259. Min Act: -0.0000

Data Index: 591023 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.3889. Min Act: -0.0000

Data Index: 293462 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.3391. Min Act: -0.0000

Data Index: 563494 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.3019. Min Act: -0.0000

Data Index: 546967 (The Pile)

Max Activating Token Index: 29

Text #18

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.2955. Min Act: -0.0000

Data Index: 533556 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.4114. Min Act: -0.0000

Data Index: 1742464 (The Pile)

Max Activating Token Index: 501