Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 763 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0154. Min Act: -0.0006

Data Index: 49106 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0006

Data Index: 487008 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1299920 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0153. Min Act: -0.0006

Data Index: 614226 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0151. Min Act: -0.0006

Data Index: 506302 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1221383 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0142. Min Act: -0.0006

Data Index: 281739 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0145. Min Act: -0.0006

Data Index: 535532 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0006

Data Index: 336245 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1255644 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0006

Data Index: 519708 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1060213 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0140. Min Act: -0.0006

Data Index: 392433 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0137. Min Act: -0.0006

Data Index: 313083 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1279286 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1205299 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0138. Min Act: -0.0006

Data Index: 564140 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1011515 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0135. Min Act: -0.0006

Data Index: 434361 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0138. Min Act: -0.0006

Data Index: 363445 (C4 (Web Text))

Max Activating Token Index: 663