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

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

Neuron 1605 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1195964 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0168. Min Act: -0.0003

Data Index: 219927 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0167. Min Act: -0.0003

Data Index: 56981 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0163. Min Act: -0.0003

Data Index: 75872 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0153. Min Act: -0.0003

Data Index: 386343 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1077121 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1223644 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0141. Min Act: -0.0003

Data Index: 931930 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0140. Min Act: -0.0003

Data Index: 267342 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0139. Min Act: -0.0003

Data Index: 470734 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0139. Min Act: -0.0003

Data Index: 1099843 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0138. Min Act: -0.0003

Data Index: 420528 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0135. Min Act: -0.0003

Data Index: 649254 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1538665 (Python Code)

Max Activating Token Index: 2

Text #14

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1389272 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1505138 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1636523 (Python Code)

Max Activating Token Index: 2

Text #17

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1479004 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1571288 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1371706 (Python Code)

Max Activating Token Index: 2