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

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

Neuron 3681 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: 0.7982. Min Range: -0.7982

Max Act: 0.7982. Min Act: -0.0000

Data Index: 267066 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5437. Min Act: -0.0000

Data Index: 354280 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5343. Min Act: -0.0000

Data Index: 158924 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1227401 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4442. Min Act: -0.0000

Data Index: 925494 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4125. Min Act: -0.0000

Data Index: 63044 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4378. Min Act: -0.0000

Data Index: 212464 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4315. Min Act: -0.0000

Data Index: 36464 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4399. Min Act: -0.0000

Data Index: 232979 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4401. Min Act: -0.0000

Data Index: 644300 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4549. Min Act: -0.0000

Data Index: 45520 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.3999. Min Act: -0.0000

Data Index: 896156 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1354325 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4030. Min Act: -0.0000

Data Index: 248011 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1039554 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.3900. Min Act: -0.0000

Data Index: 544049 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1157067 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1004687 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1021080 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.3959. Min Act: -0.0000

Data Index: 28405 (C4 (Web Text))

Max Activating Token Index: 880