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

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

Neuron 5929 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2174. Min Range: -1.2174

Max Act: 1.2174. Min Act: 0.0000

Data Index: 236525 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1278567 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1111535 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1300079 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.9306. Min Act: 0.0000

Data Index: 698926 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.8313. Min Act: -0.0000

Data Index: 814385 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.7748. Min Act: 0.0000

Data Index: 150492 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.8073. Min Act: 0.0000

Data Index: 1186183 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.7462. Min Act: 0.0000

Data Index: 212731 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.7592. Min Act: -0.0000

Data Index: 957277 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1334271 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1217306 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.6967. Min Act: -0.0000

Data Index: 368711 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.6457. Min Act: -0.0000

Data Index: 427361 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1341354 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.6229. Min Act: 0.0000

Data Index: 650452 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.6395. Min Act: 0.0000

Data Index: 295061 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.6327. Min Act: -0.0000

Data Index: 816279 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.6269. Min Act: -0.0000

Data Index: 717105 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.6224. Min Act: -0.0000

Data Index: 511349 (C4 (Web Text))

Max Activating Token Index: 458