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

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

Neuron 4286 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.3395. Min Act: -0.0000

Data Index: 616911 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1383447 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1201322 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1646645 (Python Code)

Max Activating Token Index: 370

Text #4

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1270009 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.3049. Min Act: -0.0000

Data Index: 563348 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1151979 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2878. Min Act: -0.0000

Data Index: 395119 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2876. Min Act: -0.0000

Data Index: 876199 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2576. Min Act: -0.0000

Data Index: 138966 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2916. Min Act: -0.0000

Data Index: 890111 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2819. Min Act: -0.0000

Data Index: 898548 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2717. Min Act: -0.0000

Data Index: 885166 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1570005 (Python Code)

Max Activating Token Index: 401

Text #14

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1073625 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2650. Min Act: -0.0000

Data Index: 893296 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1317616 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2505. Min Act: -0.0000

Data Index: 339023 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1402992 (Python Code)

Max Activating Token Index: 812

Text #19

Max Range: 0.3395. Min Range: -0.3395

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1538493 (Python Code)

Max Activating Token Index: 433