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

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

Neuron 4303 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.6284. Min Act: -0.0000

Data Index: 227662 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.4572. Min Act: -0.0000

Data Index: 845913 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.4215. Min Act: -0.0000

Data Index: 835780 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.4733. Min Act: -0.0000

Data Index: 233597 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.3479. Min Act: -0.0000

Data Index: 1242477 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.2316. Min Act: -0.0000

Data Index: 175543 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.3514. Min Act: -0.0000

Data Index: 989834 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.3169. Min Act: -0.0000

Data Index: 71477 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.2325. Min Act: -0.0000

Data Index: 157334 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.1242. Min Act: -0.0000

Data Index: 676886 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.1941. Min Act: -0.0000

Data Index: 739362 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.1717. Min Act: -0.0000

Data Index: 973569 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.1584. Min Act: -0.0000

Data Index: 522035 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.1366. Min Act: -0.0000

Data Index: 914946 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.1412. Min Act: -0.0000

Data Index: 457237 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.1216. Min Act: -0.0000

Data Index: 140869 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.1177. Min Act: -0.0000

Data Index: 374215 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.1175. Min Act: -0.0000

Data Index: 894081 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.0906. Min Act: -0.0000

Data Index: 827373 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.0860. Min Act: -0.0000

Data Index: 212153 (C4 (Web Text))

Max Activating Token Index: 238