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

Dataset: The Pile

Neuron 2779 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: 1.8616. Min Range: -1.8616

Max Act: 1.8616. Min Act: -0.0000

Data Index: 1433359 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.7844. Min Act: -0.0000

Data Index: 582605 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.6139. Min Act: -0.0000

Data Index: 188424 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5298. Min Act: -0.0000

Data Index: 194578 (The Pile)

Max Activating Token Index: 605

Text #4

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4530. Min Act: -0.0000

Data Index: 310170 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.3898. Min Act: -0.0000

Data Index: 124362 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4950. Min Act: -0.0000

Data Index: 317592 (The Pile)

Max Activating Token Index: 749

Text #7

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1737744 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.3367. Min Act: -0.0000

Data Index: 906844 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.2204. Min Act: -0.0000

Data Index: 1607977 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.2619. Min Act: -0.0000

Data Index: 436969 (The Pile)

Max Activating Token Index: 390

Text #11

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1535687 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.2450. Min Act: -0.0000

Data Index: 1542274 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.2358. Min Act: -0.0000

Data Index: 862378 (The Pile)

Max Activating Token Index: 358

Text #14

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.1698. Min Act: -0.0000

Data Index: 219716 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.1398. Min Act: -0.0000

Data Index: 442480 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.1964. Min Act: -0.0000

Data Index: 1249466 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.1174. Min Act: -0.0000

Data Index: 297478 (The Pile)

Max Activating Token Index: 854

Text #18

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1339745 (The Pile)

Max Activating Token Index: 955

Text #19

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1463815 (The Pile)

Max Activating Token Index: 373