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

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

Neuron 5506 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: 0.0191. Min Range: -0.0191

Max Act: 0.0191. Min Act: -0.0002

Data Index: 82504 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1622227 (Python Code)

Max Activating Token Index: 230

Text #2

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0143. Min Act: -0.0002

Data Index: 368283 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1238984 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1329706 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0163. Min Act: -0.0002

Data Index: 889396 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1240635 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0151. Min Act: -0.0002

Data Index: 99595 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1192776 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0162. Min Act: -0.0002

Data Index: 120941 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1545408 (Python Code)

Max Activating Token Index: 445

Text #12

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0152. Min Act: -0.0002

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1299844 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1022504 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1551483 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0142. Min Act: -0.0002

Data Index: 263127 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1053331 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0135. Min Act: -0.0002

Data Index: 361488 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0136. Min Act: -0.0002

Data Index: 65884 (C4 (Web Text))

Max Activating Token Index: 499