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

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

Neuron 2298 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.2302. Min Act: -0.0001

Data Index: 967110 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1103521 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1874. Min Act: -0.0001

Data Index: 325119 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1731. Min Act: -0.0001

Data Index: 480781 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1685. Min Act: -0.0000

Data Index: 475538 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1810. Min Act: -0.0001

Data Index: 571632 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1799. Min Act: -0.0001

Data Index: 713846 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1592. Min Act: -0.0001

Data Index: 31188 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1488. Min Act: -0.0001

Data Index: 808127 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1597. Min Act: -0.0001

Data Index: 712059 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1058854 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1453. Min Act: -0.0000

Data Index: 440780 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1601. Min Act: -0.0001

Data Index: 234822 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1636. Min Act: -0.0001

Data Index: 949926 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1585. Min Act: -0.0001

Data Index: 741154 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1187589 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1568. Min Act: -0.0000

Data Index: 673408 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1568. Min Act: -0.0001

Data Index: 250142 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1550. Min Act: -0.0001

Data Index: 169093 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1290758 (C4 (Web Text))

Max Activating Token Index: 721