Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 121 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.7780. Min Act: -0.0001

Data Index: 697132 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6069. Min Act: -0.0001

Data Index: 31680 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1102915 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5658. Min Act: -0.0001

Data Index: 543062 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5671. Min Act: -0.0001

Data Index: 1282899 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5443. Min Act: -0.0001

Data Index: 140068 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1215548 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4936. Min Act: -0.0001

Data Index: 74139 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5706. Min Act: -0.0001

Data Index: 1099616 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5254. Min Act: -0.0000

Data Index: 911367 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5392. Min Act: -0.0001

Data Index: 166790 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5312. Min Act: -0.0001

Data Index: 1094631 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4981. Min Act: -0.0001

Data Index: 942119 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5469. Min Act: -0.0001

Data Index: 249737 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4915. Min Act: -0.0001

Data Index: 361048 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5549. Min Act: -0.0000

Data Index: 596203 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1327949 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5342. Min Act: -0.0000

Data Index: 552509 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5454. Min Act: -0.0000

Data Index: 906524 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5568. Min Act: -0.0001

Data Index: 1275813 (C4 (Web Text))

Max Activating Token Index: 940