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

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

Neuron 5442 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: 1.2580. Min Range: -1.2580

Max Act: 1.2580. Min Act: -0.0000

Data Index: 778684 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 1.2580. Min Range: -1.2580

Max Act: 1.1475. Min Act: -0.0000

Data Index: 1288309 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.9328. Min Act: 0.0000

Data Index: 987781 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.9252. Min Act: -0.0000

Data Index: 206544 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1359231 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.7498. Min Act: -0.0000

Data Index: 35473 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.7144. Min Act: -0.0000

Data Index: 772907 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6680. Min Act: 0.0000

Data Index: 288200 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6981. Min Act: -0.0000

Data Index: 206479 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1073883 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.7038. Min Act: -0.0000

Data Index: 576601 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1313018 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1005380 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1243551 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1066853 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6532. Min Act: -0.0000

Data Index: 928390 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6677. Min Act: 0.0000

Data Index: 923265 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6920. Min Act: -0.0000

Data Index: 465357 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6134. Min Act: -0.0000

Data Index: 627057 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 1.2580. Min Range: -1.2580

Max Act: 0.6167. Min Act: -0.0000

Data Index: 493197 (C4 (Web Text))

Max Activating Token Index: 134