Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2745 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0210. Min Act: -0.0004

Data Index: 17691 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0209. Min Act: -0.0004

Data Index: 658057 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0189. Min Act: -0.0004

Data Index: 1415343 (Python Code)

Max Activating Token Index: 609

Text #3

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0172. Min Act: -0.0004

Data Index: 720031 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0169. Min Act: -0.0004

Data Index: 566330 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0166. Min Act: -0.0004

Data Index: 982527 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0162. Min Act: -0.0004

Data Index: 373312 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0169. Min Act: -0.0004

Data Index: 479567 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0157. Min Act: -0.0004

Data Index: 142285 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0152. Min Act: -0.0004

Data Index: 787390 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0158. Min Act: -0.0004

Data Index: 323513 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0157. Min Act: -0.0004

Data Index: 1078871 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0153. Min Act: -0.0004

Data Index: 533198 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0149. Min Act: -0.0004

Data Index: 758290 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0137. Min Act: -0.0004

Data Index: 779079 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0147. Min Act: -0.0004

Data Index: 25438 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0145. Min Act: -0.0004

Data Index: 231375 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0150. Min Act: -0.0004

Data Index: 143803 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0146. Min Act: -0.0004

Data Index: 41510 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0134. Min Act: -0.0004

Data Index: 1299314 (C4 (Web Text))

Max Activating Token Index: 586