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

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

Neuron 1189 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.5192. Min Act: -0.0000

Data Index: 106583 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.4911. Min Act: -0.0000

Data Index: 1213915 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.3936. Min Act: -0.0000

Data Index: 664633 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.4602. Min Act: -0.0000

Data Index: 928376 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.4525. Min Act: -0.0000

Data Index: 205542 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.4248. Min Act: 0.0000

Data Index: 1096328 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.4119. Min Act: -0.0000

Data Index: 746776 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.4959. Min Act: -0.0000

Data Index: 1192842 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.3992. Min Act: -0.0000

Data Index: 978154 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.3753. Min Act: -0.0000

Data Index: 787560 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.4123. Min Act: -0.0000

Data Index: 717527 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.3002. Min Act: -0.0000

Data Index: 384356 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.3354. Min Act: -0.0000

Data Index: 916942 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.3170. Min Act: -0.0000

Data Index: 277761 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.2989. Min Act: -0.0000

Data Index: 862693 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.2597. Min Act: -0.0000

Data Index: 9540 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1331591 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.2608. Min Act: -0.0000

Data Index: 704177 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.2884. Min Act: -0.0000

Data Index: 468919 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 1.5192. Min Range: -1.5192

Max Act: 1.2429. Min Act: -0.0000

Data Index: 246982 (C4 (Web Text))

Max Activating Token Index: 65