Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5765 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0192. Min Act: -0.0002

Data Index: 1471571 (Python Code)

Max Activating Token Index: 195

Text #1

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1415023 (Python Code)

Max Activating Token Index: 389

Text #2

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0168. Min Act: -0.0002

Data Index: 192173 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0174. Min Act: -0.0002

Data Index: 146374 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1579300 (Python Code)

Max Activating Token Index: 347

Text #5

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0185. Min Act: -0.0002

Data Index: 392057 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0177. Min Act: -0.0002

Data Index: 521855 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1005551 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1048284 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0163. Min Act: -0.0002

Data Index: 597046 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0158. Min Act: -0.0002

Data Index: 894738 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1496722 (Python Code)

Max Activating Token Index: 401

Text #12

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1352100 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1169894 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0140. Min Act: -0.0002

Data Index: 527430 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0142. Min Act: -0.0002

Data Index: 177664 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0143. Min Act: -0.0002

Data Index: 496030 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1318165 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1537621 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0134. Min Act: -0.0002

Data Index: 273050 (C4 (Web Text))

Max Activating Token Index: 949