Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5399 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.3143. Min Act: -0.0000

Data Index: 742906 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2818. Min Act: -0.0000

Data Index: 235889 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.3064. Min Act: -0.0000

Data Index: 263837 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1057047 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2972. Min Act: -0.0000

Data Index: 543791 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2880. Min Act: -0.0000

Data Index: 209959 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2769. Min Act: -0.0000

Data Index: 228059 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2848. Min Act: -0.0000

Data Index: 686933 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2863. Min Act: -0.0000

Data Index: 775115 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1161858 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2601. Min Act: -0.0000

Data Index: 319344 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2823. Min Act: -0.0000

Data Index: 233206 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2753. Min Act: -0.0000

Data Index: 490416 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2623. Min Act: -0.0000

Data Index: 308812 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2518. Min Act: -0.0000

Data Index: 605351 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2192. Min Act: -0.0000

Data Index: 289411 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2515. Min Act: -0.0000

Data Index: 96239 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2724. Min Act: -0.0000

Data Index: 855511 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2393. Min Act: -0.0000

Data Index: 138695 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1098843 (C4 (Web Text))

Max Activating Token Index: 726