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

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

Neuron 1054 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4972. Min Act: -0.0000

Data Index: 959134 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2584. Min Act: -0.0000

Data Index: 359161 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.1533. Min Act: -0.0000

Data Index: 49326 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0759. Min Act: -0.0000

Data Index: 641441 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0657. Min Act: -0.0000

Data Index: 965430 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0788. Min Act: -0.0000

Data Index: 81545 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1062114 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1123234 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0003. Min Act: -0.0000

Data Index: 120727 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9997. Min Act: -0.0000

Data Index: 752097 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1272986 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0460. Min Act: -0.0000

Data Index: 599026 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9842. Min Act: -0.0000

Data Index: 118853 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9768. Min Act: -0.0000

Data Index: 1166459 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1143437 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1222420 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0172. Min Act: -0.0000

Data Index: 1337568 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9885. Min Act: -0.0000

Data Index: 628077 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1120458 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0052. Min Act: -0.0000

Data Index: 840033 (C4 (Web Text))

Max Activating Token Index: 755