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

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

Neuron 645 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: 0.0175. Min Range: -0.0175

Max Act: 0.0175. Min Act: -0.0006

Data Index: 82312 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1366169 (Python Code)

Max Activating Token Index: 380

Text #2

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0166. Min Act: -0.0006

Data Index: 677625 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1498858 (Python Code)

Max Activating Token Index: 604

Text #4

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1628803 (Python Code)

Max Activating Token Index: 843

Text #5

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1576977 (Python Code)

Max Activating Token Index: 749

Text #6

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1368662 (Python Code)

Max Activating Token Index: 192

Text #7

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1448702 (Python Code)

Max Activating Token Index: 130

Text #8

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0155. Min Act: -0.0006

Data Index: 711187 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1633448 (Python Code)

Max Activating Token Index: 546

Text #10

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1524507 (Python Code)

Max Activating Token Index: 561

Text #11

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0155. Min Act: -0.0006

Data Index: 549999 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0158. Min Act: -0.0006

Data Index: 48905 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0154. Min Act: -0.0006

Data Index: 334715 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1514827 (Python Code)

Max Activating Token Index: 601

Text #15

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1602143 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0151. Min Act: -0.0006

Data Index: 835812 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0151. Min Act: -0.0006

Data Index: 677305 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1654851 (Python Code)

Max Activating Token Index: 40

Text #19

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1455070 (Python Code)

Max Activating Token Index: 31