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

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

Neuron 628 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4824. Min Act: -0.0000

Data Index: 84696 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3985. Min Act: -0.0000

Data Index: 246482 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1355198 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4163. Min Act: -0.0000

Data Index: 879771 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3627. Min Act: -0.0000

Data Index: 211816 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3923. Min Act: -0.0000

Data Index: 114139 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1308011 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3766. Min Act: -0.0000

Data Index: 168652 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3978. Min Act: -0.0000

Data Index: 970508 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1117505 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3628. Min Act: -0.0000

Data Index: 923682 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3736. Min Act: -0.0000

Data Index: 591879 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1238842 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3346. Min Act: -0.0000

Data Index: 679322 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3475. Min Act: -0.0000

Data Index: 902234 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1275021 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3339. Min Act: -0.0000

Data Index: 814114 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3414. Min Act: -0.0000

Data Index: 933313 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3382. Min Act: -0.0000

Data Index: 340347 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3262. Min Act: -0.0000

Data Index: 687345 (C4 (Web Text))

Max Activating Token Index: 614