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

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

Neuron 3104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.8159. Min Act: -0.0000

Data Index: 579941 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.8550. Min Act: -0.0000

Data Index: 564433 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.8129. Min Act: -0.0000

Data Index: 465157 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1317296 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.7380. Min Act: -0.0000

Data Index: 825415 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.7468. Min Act: -0.0000

Data Index: 743439 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6762. Min Act: -0.0000

Data Index: 803962 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6627. Min Act: -0.0000

Data Index: 510876 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6648. Min Act: -0.0000

Data Index: 632895 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.7190. Min Act: -0.0000

Data Index: 989995 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1344217 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6669. Min Act: -0.0000

Data Index: 592478 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6622. Min Act: -0.0000

Data Index: 627454 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1291126 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1101796 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6728. Min Act: -0.0000

Data Index: 776944 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6517. Min Act: -0.0000

Data Index: 883705 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1118447 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6856. Min Act: -0.0000

Data Index: 902228 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6895. Min Act: -0.0000

Data Index: 34550 (C4 (Web Text))

Max Activating Token Index: 191