Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 672 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0003

Data Index: 608420 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1421996 (Python Code)

Max Activating Token Index: 557

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1214425 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0177. Min Act: -0.0003

Data Index: 124099 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1065075 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1433629 (Python Code)

Max Activating Token Index: 783

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0190. Min Act: -0.0003

Data Index: 54002 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0162. Min Act: -0.0003

Data Index: 110676 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1141020 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1568833 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1483460 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1643735 (Python Code)

Max Activating Token Index: 639

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0160. Min Act: -0.0003

Data Index: 309289 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0185. Min Act: -0.0003

Data Index: 48663 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1498222 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1372649 (Python Code)

Max Activating Token Index: 563

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0150. Min Act: -0.0003

Data Index: 573120 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1296018 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0135. Min Act: -0.0003

Data Index: 266635 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0151. Min Act: -0.0003

Data Index: 249082 (C4 (Web Text))

Max Activating Token Index: 279