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

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

Neuron 2421 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.7883. Min Act: -0.0000

Data Index: 731942 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.7487. Min Act: -0.0000

Data Index: 229792 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.7461. Min Act: -0.0000

Data Index: 400275 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.7520. Min Act: -0.0000

Data Index: 787764 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.7153. Min Act: -0.0000

Data Index: 742090 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.7572. Min Act: -0.0001

Data Index: 333749 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6956. Min Act: -0.0001

Data Index: 904362 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.7244. Min Act: -0.0001

Data Index: 6349 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1145277 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.7262. Min Act: -0.0000

Data Index: 128053 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.7197. Min Act: -0.0000

Data Index: 637445 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6981. Min Act: -0.0000

Data Index: 198366 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1134637 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6812. Min Act: -0.0000

Data Index: 691752 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6766. Min Act: -0.0000

Data Index: 124118 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6759. Min Act: -0.0000

Data Index: 81637 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6932. Min Act: -0.0000

Data Index: 306111 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6422. Min Act: -0.0000

Data Index: 262522 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6812. Min Act: -0.0001

Data Index: 601230 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6597. Min Act: -0.0000

Data Index: 873277 (C4 (Web Text))

Max Activating Token Index: 717