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

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

Neuron 528 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1314570 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4285. Min Act: -0.0000

Data Index: 280137 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3073. Min Act: -0.0001

Data Index: 346437 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4599. Min Act: -0.0001

Data Index: 575181 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3671. Min Act: -0.0000

Data Index: 472778 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3490. Min Act: -0.0000

Data Index: 491171 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3141. Min Act: -0.0000

Data Index: 918633 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2212. Min Act: -0.0001

Data Index: 168606 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2062. Min Act: -0.0000

Data Index: 103501 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2698. Min Act: -0.0001

Data Index: 283746 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2622. Min Act: -0.0001

Data Index: 546108 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1766. Min Act: -0.0001

Data Index: 102459 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1657. Min Act: -0.0000

Data Index: 231738 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3165. Min Act: -0.0000

Data Index: 37239 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2001. Min Act: -0.0000

Data Index: 7588 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1022933 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2675. Min Act: -0.0001

Data Index: 10259 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1216. Min Act: -0.0001

Data Index: 44017 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1807. Min Act: -0.0000

Data Index: 970301 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2553. Min Act: -0.0000

Data Index: 832629 (C4 (Web Text))

Max Activating Token Index: 345