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

Dataset: The Pile

Neuron 697 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.3364. Min Act: -0.0000

Data Index: 150139 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.1025. Min Act: -0.0000

Data Index: 318293 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1232709 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0266. Min Act: 0.0000

Data Index: 1617945 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8250. Min Act: -0.0000

Data Index: 3460 (The Pile)

Max Activating Token Index: 715

Text #5

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1412787 (The Pile)

Max Activating Token Index: 731

Text #6

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1543430 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9141. Min Act: -0.0000

Data Index: 373229 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1990162 (The Pile)

Max Activating Token Index: 613

Text #9

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1654021 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1178109 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1390475 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1241665 (The Pile)

Max Activating Token Index: 403

Text #13

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.7385. Min Act: -0.0000

Data Index: 525879 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1246506 (The Pile)

Max Activating Token Index: 973

Text #15

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1222230 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.7902. Min Act: -0.0000

Data Index: 59707 (The Pile)

Max Activating Token Index: 598

Text #17

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8089. Min Act: -0.0000

Data Index: 496897 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8861. Min Act: -0.0000

Data Index: 914356 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1140031 (The Pile)

Max Activating Token Index: 892