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

Dataset: The Pile

Neuron 3665 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7391. Min Range: -3.7391

Max Act: 3.7391. Min Act: -0.0000

Data Index: 1028665 (The Pile)

Max Activating Token Index: 779

Text #1

Max Range: 3.7391. Min Range: -3.7391

Max Act: 3.4330. Min Act: -0.0000

Data Index: 1010568 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 3.7391. Min Range: -3.7391

Max Act: 3.4152. Min Act: -0.0000

Data Index: 1457925 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 3.7391. Min Range: -3.7391

Max Act: 3.6725. Min Act: -0.0000

Data Index: 1743723 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 3.7391. Min Range: -3.7391

Max Act: 3.0064. Min Act: -0.0000

Data Index: 1294824 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 3.7391. Min Range: -3.7391

Max Act: 3.1195. Min Act: -0.0000

Data Index: 613378 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 3.7391. Min Range: -3.7391

Max Act: 3.0181. Min Act: -0.0000

Data Index: 1005412 (The Pile)

Max Activating Token Index: 305

Text #7

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.8227. Min Act: -0.0000

Data Index: 1030027 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.8096. Min Act: -0.0000

Data Index: 712484 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.6943. Min Act: -0.0000

Data Index: 1413357 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.5911. Min Act: -0.0000

Data Index: 421968 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.5945. Min Act: -0.0000

Data Index: 1158627 (The Pile)

Max Activating Token Index: 467

Text #12

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.5601. Min Act: -0.0000

Data Index: 900619 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.8123. Min Act: -0.0000

Data Index: 1904769 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.6709. Min Act: -0.0000

Data Index: 823315 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.6216. Min Act: -0.0000

Data Index: 370639 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.5923. Min Act: -0.0000

Data Index: 1767998 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.5885. Min Act: -0.0000

Data Index: 1095465 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.4200. Min Act: -0.0000

Data Index: 526652 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 3.7391. Min Range: -3.7391

Max Act: 2.5301. Min Act: -0.0000

Data Index: 1201305 (The Pile)

Max Activating Token Index: 370