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

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

Neuron 3184 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5575. Min Act: -0.0000

Data Index: 1026843 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4191. Min Act: -0.0000

Data Index: 615401 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4075. Min Act: -0.0000

Data Index: 256223 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3420. Min Act: -0.0000

Data Index: 827828 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3043. Min Act: -0.0000

Data Index: 67248 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1255454 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1410524 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1669. Min Act: -0.0000

Data Index: 275593 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1654. Min Act: -0.0000

Data Index: 1313646 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1844. Min Act: -0.0000

Data Index: 885874 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1304. Min Act: -0.0000

Data Index: 272505 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.0243. Min Act: -0.0000

Data Index: 47359 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1272. Min Act: -0.0000

Data Index: 1099074 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.0565. Min Act: -0.0000

Data Index: 778563 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 1.5575. Min Range: -1.5575

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1497115 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1146. Min Act: -0.0000

Data Index: 65752 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1120. Min Act: -0.0000

Data Index: 306978 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1012. Min Act: -0.0000

Data Index: 1193111 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1380514 (Python Code)

Max Activating Token Index: 347

Text #19

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.0018. Min Act: -0.0000

Data Index: 861552 (C4 (Web Text))

Max Activating Token Index: 351