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

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

Neuron 4127 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.8332. Min Act: -0.0000

Data Index: 893958 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1602778 (Python Code)

Max Activating Token Index: 52

Text #2

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7740. Min Act: -0.0000

Data Index: 234271 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1056975 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1405302 (Python Code)

Max Activating Token Index: 895

Text #5

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.8150. Min Act: -0.0000

Data Index: 29972 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7375. Min Act: -0.0000

Data Index: 722422 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1335012 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7190. Min Act: -0.0000

Data Index: 270356 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7079. Min Act: -0.0000

Data Index: 21387 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1149101 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6508. Min Act: -0.0000

Data Index: 447558 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6368. Min Act: -0.0000

Data Index: 974847 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6095. Min Act: -0.0000

Data Index: 749064 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1598768 (Python Code)

Max Activating Token Index: 824

Text #15

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6188. Min Act: -0.0000

Data Index: 143132 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5690. Min Act: -0.0000

Data Index: 878938 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5353. Min Act: -0.0000

Data Index: 935845 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6245. Min Act: -0.0000

Data Index: 56867 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5718. Min Act: -0.0000

Data Index: 220194 (C4 (Web Text))

Max Activating Token Index: 963