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

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

Neuron 3979 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: 0.3464. Min Range: -0.3464

Max Act: 0.3464. Min Act: -0.0000

Data Index: 708135 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2990. Min Act: -0.0000

Data Index: 415006 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2420. Min Act: -0.0000

Data Index: 486703 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2475. Min Act: -0.0000

Data Index: 892022 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1350270 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2102. Min Act: -0.0000

Data Index: 303721 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2092. Min Act: -0.0000

Data Index: 577521 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2109. Min Act: -0.0000

Data Index: 812587 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1205. Min Act: -0.0000

Data Index: 172655 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2070. Min Act: -0.0000

Data Index: 716677 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1989. Min Act: -0.0000

Data Index: 145151 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2007. Min Act: -0.0000

Data Index: 270086 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1359652 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1904. Min Act: -0.0000

Data Index: 1241344 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1287446 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1958. Min Act: -0.0000

Data Index: 442231 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1767. Min Act: -0.0000

Data Index: 430321 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1855. Min Act: -0.0000

Data Index: 34342 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1327910 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1825. Min Act: -0.0000

Data Index: 978044 (C4 (Web Text))

Max Activating Token Index: 896