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

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

Neuron 5913 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5990. Min Range: -3.5990

Max Act: 3.5990. Min Act: -0.0000

Data Index: 598291 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 3.5990. Min Range: -3.5990

Max Act: 3.4500. Min Act: -0.0000

Data Index: 1257533 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 3.5990. Min Range: -3.5990

Max Act: 3.4439. Min Act: -0.0000

Data Index: 537090 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 3.5990. Min Range: -3.5990

Max Act: 3.3995. Min Act: -0.0000

Data Index: 1274503 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 3.5990. Min Range: -3.5990

Max Act: 3.1447. Min Act: -0.0000

Data Index: 975106 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 3.5990. Min Range: -3.5990

Max Act: 3.2582. Min Act: -0.0000

Data Index: 908728 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.9673. Min Act: -0.0000

Data Index: 310237 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.8123. Min Act: -0.0000

Data Index: 761042 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.9775. Min Act: -0.0000

Data Index: 994206 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 3.5990. Min Range: -3.5990

Max Act: 3.1017. Min Act: -0.0000

Data Index: 1329516 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.9075. Min Act: -0.0000

Data Index: 1296037 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 3.5990. Min Range: -3.5990

Max Act: 3.0332. Min Act: -0.0000

Data Index: 215790 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.8891. Min Act: -0.0000

Data Index: 452324 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.8161. Min Act: -0.0000

Data Index: 27095 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.6583. Min Act: -0.0000

Data Index: 1272587 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.9445. Min Act: -0.0000

Data Index: 365013 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.6508. Min Act: -0.0000

Data Index: 861136 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.7536. Min Act: -0.0000

Data Index: 434217 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.5727. Min Act: -0.0000

Data Index: 888037 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 3.5990. Min Range: -3.5990

Max Act: 2.6901. Min Act: -0.0000

Data Index: 389053 (C4 (Web Text))

Max Activating Token Index: 132