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

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

Neuron 4169 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.3505. Min Act: -0.0000

Data Index: 372429 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.3453. Min Act: -0.0000

Data Index: 839562 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.2242. Min Act: -0.0000

Data Index: 288722 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.2423. Min Act: -0.0000

Data Index: 177859 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1190. Min Act: -0.0000

Data Index: 505935 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1408. Min Act: -0.0000

Data Index: 479660 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0942. Min Act: -0.0000

Data Index: 205874 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1292343 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0352. Min Act: 0.0000

Data Index: 46981 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0298. Min Act: -0.0000

Data Index: 726151 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0368. Min Act: -0.0000

Data Index: 687098 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0540. Min Act: -0.0000

Data Index: 336468 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1263659 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0218. Min Act: 0.0000

Data Index: 1020291 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1156992 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0133. Min Act: 0.0001

Data Index: 857240 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0043. Min Act: -0.0000

Data Index: 562187 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0071. Min Act: -0.0000

Data Index: 1347794 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0343. Min Act: 0.0002

Data Index: 61310 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1263419 (C4 (Web Text))

Max Activating Token Index: 342