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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3126 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2578. Min Range: -2.2578

Max Act: 2.2578. Min Act: -0.0000

Data Index: 175031 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 2.2578. Min Range: -2.2578

Max Act: 2.0352. Min Act: -0.0000

Data Index: 886226 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.8994. Min Act: -0.0000

Data Index: 696300 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.8719. Min Act: -0.0000

Data Index: 272374 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.8365. Min Act: -0.0000

Data Index: 1008518 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.7153. Min Act: -0.0000

Data Index: 1044159 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.6285. Min Act: -0.0000

Data Index: 522717 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.6950. Min Act: -0.0000

Data Index: 123000 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.5891. Min Act: -0.0000

Data Index: 47795 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.5824. Min Act: -0.0001

Data Index: 947537 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.6289. Min Act: -0.0000

Data Index: 348086 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.5940. Min Act: -0.0000

Data Index: 917355 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.5019. Min Act: -0.0000

Data Index: 1164356 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.6830. Min Act: -0.0000

Data Index: 262711 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.6481. Min Act: -0.0000

Data Index: 735179 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.5408. Min Act: -0.0000

Data Index: 961108 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.5374. Min Act: -0.0000

Data Index: 1356311 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.4451. Min Act: -0.0000

Data Index: 757044 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.5570. Min Act: -0.0000

Data Index: 515480 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 2.2578. Min Range: -2.2578

Max Act: 1.4595. Min Act: -0.0001

Data Index: 363077 (C4 (Web Text))

Max Activating Token Index: 858