Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2452 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.3015. Min Act: -0.0002

Data Index: 814502 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.2428. Min Act: -0.0002

Data Index: 488534 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.2435. Min Act: -0.0001

Data Index: 24602 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.2518. Min Act: -0.0002

Data Index: 49400 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1503. Min Act: -0.0002

Data Index: 906085 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.2565. Min Act: -0.0001

Data Index: 1167321 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.2047. Min Act: -0.0002

Data Index: 948886 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1505. Min Act: -0.0002

Data Index: 800502 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1226. Min Act: -0.0002

Data Index: 1185747 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1727. Min Act: -0.0002

Data Index: 1233502 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1269. Min Act: -0.0002

Data Index: 1015059 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1155. Min Act: -0.0001

Data Index: 652256 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1181. Min Act: -0.0002

Data Index: 1044042 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1385. Min Act: -0.0002

Data Index: 371719 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1018. Min Act: -0.0001

Data Index: 506018 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.0571. Min Act: -0.0002

Data Index: 8952 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 1.3015. Min Range: -1.3015

Max Act: 0.9979. Min Act: -0.0002

Data Index: 1322312 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.0762. Min Act: -0.0002

Data Index: 539688 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1036. Min Act: -0.0002

Data Index: 843575 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.0595. Min Act: -0.0002

Data Index: 360001 (C4 (Web Text))

Max Activating Token Index: 534