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

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

Neuron 281 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: 2.1335. Min Range: -2.1335

Max Act: 2.1335. Min Act: -0.0000

Data Index: 741242 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 2.1335. Min Range: -2.1335

Max Act: 2.0147. Min Act: -0.0000

Data Index: 118579 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.8701. Min Act: -0.0000

Data Index: 765634 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.9769. Min Act: -0.0000

Data Index: 559904 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.7090. Min Act: -0.0000

Data Index: 302173 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.6054. Min Act: -0.0000

Data Index: 1171516 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.6908. Min Act: -0.0000

Data Index: 512230 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5828. Min Act: -0.0000

Data Index: 1117393 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.6263. Min Act: -0.0000

Data Index: 1079851 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.6060. Min Act: -0.0000

Data Index: 1227966 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5071. Min Act: -0.0000

Data Index: 1073225 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5037. Min Act: -0.0000

Data Index: 828373 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.4887. Min Act: -0.0000

Data Index: 484726 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5637. Min Act: -0.0000

Data Index: 603002 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1048666 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5456. Min Act: -0.0000

Data Index: 467319 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5421. Min Act: -0.0000

Data Index: 1041182 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.4524. Min Act: -0.0000

Data Index: 1322104 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5380. Min Act: -0.0000

Data Index: 735083 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5215. Min Act: -0.0000

Data Index: 215192 (C4 (Web Text))

Max Activating Token Index: 666