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

Dataset: The Pile

Neuron 270 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: 0.3031. Min Range: -0.3031

Max Act: 0.3031. Min Act: -0.0000

Data Index: 144864 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2940. Min Act: -0.0000

Data Index: 685619 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1779006 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1602912 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1635175 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2540. Min Act: -0.0000

Data Index: 911816 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1515337 (The Pile)

Max Activating Token Index: 64

Text #7

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2677. Min Act: -0.0000

Data Index: 426134 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2495. Min Act: -0.0000

Data Index: 818635 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2466. Min Act: -0.0000

Data Index: 558485 (The Pile)

Max Activating Token Index: 160

Text #10

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2238. Min Act: -0.0000

Data Index: 832930 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2368. Min Act: -0.0000

Data Index: 81546 (The Pile)

Max Activating Token Index: 502

Text #12

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1026607 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2496. Min Act: -0.0000

Data Index: 860220 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1588198 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1298810 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2341. Min Act: -0.0000

Data Index: 644445 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1581286 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1170017 (The Pile)

Max Activating Token Index: 549

Text #19

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2259. Min Act: -0.0000

Data Index: 817359 (The Pile)

Max Activating Token Index: 722