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

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

Neuron 3521 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: 1.0563. Min Range: -1.0563

Max Act: 1.0563. Min Act: -0.0001

Data Index: 429142 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.7769. Min Act: -0.0000

Data Index: 790279 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.6479. Min Act: -0.0001

Data Index: 896397 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.5522. Min Act: -0.0001

Data Index: 593595 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1011401 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1332642 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.5093. Min Act: -0.0001

Data Index: 695195 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4422. Min Act: -0.0000

Data Index: 743705 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4890. Min Act: -0.0001

Data Index: 710298 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4853. Min Act: -0.0000

Data Index: 996708 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4680. Min Act: -0.0000

Data Index: 200436 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4801. Min Act: -0.0001

Data Index: 854515 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1344975 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.3685. Min Act: -0.0001

Data Index: 1087975 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.3788. Min Act: -0.0001

Data Index: 1066289 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.3504. Min Act: -0.0000

Data Index: 580809 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.3561. Min Act: -0.0001

Data Index: 679749 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.3193. Min Act: -0.0001

Data Index: 477607 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.3773. Min Act: -0.0001

Data Index: 37134 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.3323. Min Act: -0.0001

Data Index: 502245 (C4 (Web Text))

Max Activating Token Index: 236