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

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

Neuron 3645 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1292583 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.7759. Min Act: -0.0000

Data Index: 674338 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8154. Min Act: -0.0000

Data Index: 142490 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.7938. Min Act: -0.0000

Data Index: 923063 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.7567. Min Act: -0.0000

Data Index: 2241 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1329693 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.7306. Min Act: -0.0000

Data Index: 441362 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1083691 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1340008 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1229795 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6424. Min Act: -0.0000

Data Index: 76587 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6148. Min Act: -0.0000

Data Index: 84647 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1313622 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6489. Min Act: -0.0000

Data Index: 703808 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6620. Min Act: -0.0000

Data Index: 74246 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1344300 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1352543 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5885. Min Act: -0.0000

Data Index: 892991 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5818. Min Act: -0.0000

Data Index: 958602 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1257847 (C4 (Web Text))

Max Activating Token Index: 442