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

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

Neuron 1094 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.6751. Min Act: -0.0000

Data Index: 1161099 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.5577. Min Act: -0.0000

Data Index: 1341976 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.4814. Min Act: -0.0000

Data Index: 1345403 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.1249. Min Act: -0.0000

Data Index: 404504 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.9997. Min Act: -0.0000

Data Index: 997858 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.0117. Min Act: -0.0000

Data Index: 93770 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.9916. Min Act: -0.0000

Data Index: 400192 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.9306. Min Act: -0.0000

Data Index: 315862 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.8294. Min Act: -0.0000

Data Index: 677425 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.8217. Min Act: -0.0000

Data Index: 149069 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.7354. Min Act: -0.0000

Data Index: 776454 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.8105. Min Act: -0.0000

Data Index: 318744 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.8069. Min Act: -0.0000

Data Index: 530391 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.8017. Min Act: -0.0000

Data Index: 625788 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.8031. Min Act: -0.0000

Data Index: 1071958 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.6807. Min Act: -0.0000

Data Index: 756700 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.7281. Min Act: -0.0000

Data Index: 718704 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.7207. Min Act: -0.0000

Data Index: 481739 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.7044. Min Act: -0.0000

Data Index: 962413 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 2.6751. Min Range: -2.6751

Max Act: 1.7118. Min Act: -0.0000

Data Index: 1258571 (C4 (Web Text))

Max Activating Token Index: 915