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

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

Neuron 103 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1319. Min Act: -0.0000

Data Index: 661349 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1290309 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1063. Min Act: -0.0000

Data Index: 474146 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1064. Min Act: -0.0000

Data Index: 957500 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1488397 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1048856 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1578712 (Python Code)

Max Activating Token Index: 379

Text #7

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0922. Min Act: -0.0000

Data Index: 719542 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0875. Min Act: -0.0000

Data Index: 102296 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0843. Min Act: -0.0000

Data Index: 427740 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0831. Min Act: -0.0000

Data Index: 98004 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0848. Min Act: -0.0000

Data Index: 771895 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0839. Min Act: -0.0000

Data Index: 409758 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0787. Min Act: -0.0000

Data Index: 821861 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0822. Min Act: -0.0000

Data Index: 165840 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0841. Min Act: -0.0000

Data Index: 679326 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0778. Min Act: -0.0000

Data Index: 191662 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1214877 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0768. Min Act: -0.0000

Data Index: 841943 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.0795. Min Act: -0.0000

Data Index: 586814 (C4 (Web Text))

Max Activating Token Index: 857