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

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

Neuron 3195 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.3439. Min Act: -0.0000

Data Index: 535535 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.6305. Min Act: -0.0000

Data Index: 636852 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.4415. Min Act: -0.0000

Data Index: 1244176 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.3815. Min Act: -0.0000

Data Index: 461030 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.3204. Min Act: -0.0000

Data Index: 791352 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.3200. Min Act: -0.0000

Data Index: 456347 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.1598. Min Act: -0.0000

Data Index: 593260 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.1872. Min Act: -0.0000

Data Index: 1343868 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.0421. Min Act: -0.0000

Data Index: 697459 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.1264. Min Act: -0.0000

Data Index: 899348 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.0046. Min Act: -0.0000

Data Index: 137365 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.9972. Min Act: -0.0000

Data Index: 1049971 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.8701. Min Act: -0.0000

Data Index: 884763 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.0647. Min Act: -0.0000

Data Index: 1320962 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.0034. Min Act: -0.0000

Data Index: 230341 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.0016. Min Act: -0.0000

Data Index: 836410 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.1428. Min Act: -0.0000

Data Index: 265478 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.0007. Min Act: -0.0000

Data Index: 1226990 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.9999. Min Act: -0.0000

Data Index: 948620 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.0942. Min Act: -0.0000

Data Index: 407076 (C4 (Web Text))

Max Activating Token Index: 111