Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 11 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0167. Min Act: -0.0006

Data Index: 326907 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0162. Min Act: -0.0006

Data Index: 215620 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0006

Data Index: 325388 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1127325 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0163. Min Act: -0.0006

Data Index: 728060 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1198932 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0161. Min Act: -0.0006

Data Index: 893851 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1167482 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0163. Min Act: -0.0006

Data Index: 317551 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0159. Min Act: -0.0006

Data Index: 759343 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0159. Min Act: -0.0006

Data Index: 882454 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1305037 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1247392 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0158. Min Act: -0.0006

Data Index: 663441 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0157. Min Act: -0.0006

Data Index: 866721 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0154. Min Act: -0.0005

Data Index: 836281 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0157. Min Act: -0.0006

Data Index: 651692 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0160. Min Act: -0.0006

Data Index: 538548 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0159. Min Act: -0.0006

Data Index: 198170 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0155. Min Act: -0.0006

Data Index: 817852 (C4 (Web Text))

Max Activating Token Index: 619