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

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

Neuron 80 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: 0.4230. Min Range: -0.4230

Max Act: 0.4230. Min Act: -0.0000

Data Index: 30759 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.2582. Min Act: -0.0000

Data Index: 970215 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.2414. Min Act: -0.0000

Data Index: 727277 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1076769 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1963. Min Act: -0.0000

Data Index: 218978 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1739. Min Act: 0.0000

Data Index: 392623 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1625. Min Act: -0.0000

Data Index: 81963 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1511. Min Act: -0.0000

Data Index: 137349 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1153038 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1191. Min Act: -0.0000

Data Index: 569716 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1521. Min Act: -0.0000

Data Index: 928331 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1500. Min Act: -0.0000

Data Index: 297915 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1392417 (Python Code)

Max Activating Token Index: 207

Text #13

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1164083 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1227690 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.1105. Min Act: -0.0000

Data Index: 781164 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.0966. Min Act: 0.0000

Data Index: 296034 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.0832. Min Act: -0.0000

Data Index: 839159 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.0875. Min Act: -0.0000

Data Index: 939722 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1318375 (C4 (Web Text))

Max Activating Token Index: 893