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

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

Neuron 348 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: 0.0169. Min Range: -0.0169

Max Act: 0.0169. Min Act: -0.0004

Data Index: 1471779 (Python Code)

Max Activating Token Index: 412

Text #1

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0144. Min Act: -0.0004

Data Index: 537231 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0145. Min Act: -0.0004

Data Index: 1328498 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0157. Min Act: -0.0004

Data Index: 1392662 (Python Code)

Max Activating Token Index: 857

Text #4

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0146. Min Act: -0.0004

Data Index: 468149 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0152. Min Act: -0.0004

Data Index: 1173550 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0141. Min Act: -0.0004

Data Index: 3385 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0142. Min Act: -0.0004

Data Index: 867142 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0154. Min Act: -0.0004

Data Index: 1064242 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0136. Min Act: -0.0004

Data Index: 478463 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0149. Min Act: -0.0004

Data Index: 70978 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0143. Min Act: -0.0004

Data Index: 1248495 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0146. Min Act: -0.0004

Data Index: 500837 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0139. Min Act: -0.0004

Data Index: 1583764 (Python Code)

Max Activating Token Index: 602

Text #14

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0142. Min Act: -0.0004

Data Index: 132140 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0140. Min Act: -0.0004

Data Index: 181661 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0152. Min Act: -0.0004

Data Index: 235021 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0149. Min Act: -0.0004

Data Index: 1063008 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0149. Min Act: -0.0004

Data Index: 473962 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0150. Min Act: -0.0004

Data Index: 383912 (C4 (Web Text))

Max Activating Token Index: 835