Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1437 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4663. Min Act: -0.0001

Data Index: 362777 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3887. Min Act: -0.0001

Data Index: 1325322 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3681. Min Act: -0.0001

Data Index: 313412 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3476. Min Act: -0.0001

Data Index: 346030 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3446. Min Act: -0.0001

Data Index: 278557 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3305. Min Act: -0.0001

Data Index: 1182079 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3385. Min Act: -0.0001

Data Index: 158596 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3460. Min Act: -0.0001

Data Index: 467028 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3102. Min Act: -0.0001

Data Index: 216089 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3372. Min Act: -0.0001

Data Index: 45059 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3257. Min Act: -0.0001

Data Index: 1072877 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3356. Min Act: -0.0001

Data Index: 1097646 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3197. Min Act: -0.0001

Data Index: 1238353 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3178. Min Act: -0.0001

Data Index: 57672 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3147. Min Act: -0.0001

Data Index: 436122 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3193. Min Act: -0.0001

Data Index: 227099 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3164. Min Act: -0.0001

Data Index: 100829 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3058. Min Act: -0.0001

Data Index: 1013263 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3043. Min Act: -0.0001

Data Index: 77540 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3025. Min Act: -0.0001

Data Index: 1084524 (C4 (Web Text))

Max Activating Token Index: 459