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

Dataset: The Pile

Neuron 3641 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: 3.8439. Min Range: -3.8439

Max Act: 3.6997. Min Act: -0.0000

Data Index: 144511 (The Pile)

Max Activating Token Index: 175

Text #1

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.8315. Min Act: -0.0000

Data Index: 373460 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.8399. Min Act: -0.0000

Data Index: 1109686 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 3.8439. Min Range: -3.8439

Max Act: 2.9566. Min Act: -0.0000

Data Index: 312172 (The Pile)

Max Activating Token Index: 659

Text #4

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.6261. Min Act: -0.0000

Data Index: 184163 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.8110. Min Act: -0.0000

Data Index: 407971 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 3.8439. Min Range: -3.8439

Max Act: 2.6849. Min Act: -0.0000

Data Index: 1871991 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.1831. Min Act: -0.0000

Data Index: 804688 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.7997. Min Act: -0.0000

Data Index: 921103 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 3.8439. Min Range: -3.8439

Max Act: 2.9379. Min Act: -0.0000

Data Index: 731823 (The Pile)

Max Activating Token Index: 667

Text #10

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.6441. Min Act: -0.0000

Data Index: 1597596 (The Pile)

Max Activating Token Index: 683

Text #11

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.6315. Min Act: -0.0000

Data Index: 1307664 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.8439. Min Act: -0.0000

Data Index: 5853 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.1274. Min Act: -0.0000

Data Index: 1537256 (The Pile)

Max Activating Token Index: 597

Text #14

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.4952. Min Act: -0.0000

Data Index: 687136 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.1335. Min Act: -0.0000

Data Index: 1641897 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.4207. Min Act: -0.0000

Data Index: 399740 (The Pile)

Max Activating Token Index: 691

Text #17

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.0264. Min Act: -0.0000

Data Index: 1266008 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.4716. Min Act: -0.0000

Data Index: 845108 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 3.8439. Min Range: -3.8439

Max Act: 3.2409. Min Act: -0.0000

Data Index: 763286 (The Pile)

Max Activating Token Index: 539