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

Dataset: The Pile

Neuron 2989 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: 1.6553. Min Range: -1.6553

Max Act: 1.6110. Min Act: -0.0000

Data Index: 810232 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 1.6553. Min Range: -1.6553

Max Act: 1.6553. Min Act: -0.0000

Data Index: 1095769 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 1.6553. Min Range: -1.6553

Max Act: 1.2610. Min Act: -0.0000

Data Index: 28274 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 1.6553. Min Range: -1.6553

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1146370 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 1.6553. Min Range: -1.6553

Max Act: 1.1463. Min Act: -0.0000

Data Index: 342550 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 1.6553. Min Range: -1.6553

Max Act: 1.0280. Min Act: -0.0000

Data Index: 964926 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 1.6553. Min Range: -1.6553

Max Act: 1.0247. Min Act: -0.0000

Data Index: 265776 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 1.6553. Min Range: -1.6553

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1448519 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 1.6553. Min Range: -1.6553

Max Act: 1.0257. Min Act: -0.0000

Data Index: 1806266 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 1.6553. Min Range: -1.6553

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1976588 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 1.6553. Min Range: -1.6553

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1808543 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 1.6553. Min Range: -1.6553

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1638846 (The Pile)

Max Activating Token Index: 392

Text #12

Max Range: 1.6553. Min Range: -1.6553

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1614422 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 1.6553. Min Range: -1.6553

Max Act: 0.9319. Min Act: -0.0000

Data Index: 922876 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 1.6553. Min Range: -1.6553

Max Act: 0.8828. Min Act: -0.0000

Data Index: 919237 (The Pile)

Max Activating Token Index: 316

Text #15

Max Range: 1.6553. Min Range: -1.6553

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1583927 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 1.6553. Min Range: -1.6553

Max Act: 0.8463. Min Act: -0.0000

Data Index: 216607 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 1.6553. Min Range: -1.6553

Max Act: 0.8835. Min Act: -0.0000

Data Index: 152257 (The Pile)

Max Activating Token Index: 503

Text #18

Max Range: 1.6553. Min Range: -1.6553

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1086980 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 1.6553. Min Range: -1.6553

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1535520 (The Pile)

Max Activating Token Index: 348