Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1840 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3491. Min Act: -0.0000

Data Index: 177901 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3506. Min Act: -0.0000

Data Index: 714078 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3531. Min Act: -0.0000

Data Index: 508050 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3608. Min Act: -0.0000

Data Index: 170119 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3207. Min Act: -0.0000

Data Index: 112732 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3470. Min Act: -0.0000

Data Index: 692117 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1145198 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3097. Min Act: -0.0000

Data Index: 83676 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3107. Min Act: -0.0001

Data Index: 830938 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3274. Min Act: -0.0000

Data Index: 858567 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3049. Min Act: -0.0000

Data Index: 258186 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3047. Min Act: -0.0000

Data Index: 935135 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3402. Min Act: -0.0000

Data Index: 822846 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3316. Min Act: -0.0000

Data Index: 315151 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3281. Min Act: -0.0000

Data Index: 872393 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3184. Min Act: -0.0000

Data Index: 523384 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1187215 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3069. Min Act: -0.0000

Data Index: 515438 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1162563 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.2594. Min Act: -0.0000

Data Index: 549562 (C4 (Web Text))

Max Activating Token Index: 292