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

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

Neuron 3090 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1082181 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.8158. Min Act: -0.0000

Data Index: 964810 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7040. Min Act: -0.0000

Data Index: 413163 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1228621 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6635. Min Act: -0.0000

Data Index: 32309 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7031. Min Act: -0.0000

Data Index: 284674 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1290380 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7528. Min Act: -0.0000

Data Index: 333777 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7168. Min Act: -0.0000

Data Index: 215478 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6706. Min Act: -0.0000

Data Index: 522620 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7335. Min Act: -0.0000

Data Index: 887535 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7198. Min Act: -0.0000

Data Index: 242125 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1322916 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7484. Min Act: -0.0000

Data Index: 431724 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1429424 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6688. Min Act: -0.0000

Data Index: 95220 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1641466 (Python Code)

Max Activating Token Index: 501

Text #17

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1637782 (Python Code)

Max Activating Token Index: 399

Text #18

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6177. Min Act: -0.0000

Data Index: 694896 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1462045 (Python Code)

Max Activating Token Index: 985