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

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

Neuron 4471 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: 1.1624. Min Range: -1.1624

Max Act: 1.1624. Min Act: -0.0000

Data Index: 241963 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.1397. Min Act: -0.0000

Data Index: 973960 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1316679 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.1172. Min Act: -0.0000

Data Index: 147270 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.1364. Min Act: -0.0000

Data Index: 716375 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0694. Min Act: -0.0000

Data Index: 662775 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0614. Min Act: -0.0000

Data Index: 627222 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0279. Min Act: -0.0000

Data Index: 967677 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0700. Min Act: -0.0000

Data Index: 823859 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0112. Min Act: -0.0000

Data Index: 283043 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9901. Min Act: -0.0000

Data Index: 501590 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0044. Min Act: -0.0000

Data Index: 911870 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1286732 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0000. Min Act: -0.0000

Data Index: 822957 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8681. Min Act: -0.0000

Data Index: 1083219 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1226914 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8404. Min Act: -0.0000

Data Index: 211134 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8117. Min Act: -0.0000

Data Index: 777032 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1002192 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.7953. Min Act: -0.0000

Data Index: 753710 (C4 (Web Text))

Max Activating Token Index: 329