Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2450 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1148389 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0160. Min Act: -0.0002

Data Index: 178922 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0157. Min Act: -0.0002

Data Index: 34735 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0153. Min Act: -0.0002

Data Index: 321401 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1250186 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0153. Min Act: -0.0002

Data Index: 510544 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0153. Min Act: -0.0002

Data Index: 269764 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0152. Min Act: -0.0002

Data Index: 547700 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1000123 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1231804 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0150. Min Act: -0.0002

Data Index: 532822 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0147. Min Act: -0.0002

Data Index: 790285 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0146. Min Act: -0.0002

Data Index: 854974 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0146. Min Act: -0.0002

Data Index: 809399 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0148. Min Act: -0.0002

Data Index: 402458 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0146. Min Act: -0.0002

Data Index: 362541 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1167487 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1353106 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0144. Min Act: -0.0002

Data Index: 21306 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1006729 (C4 (Web Text))

Max Activating Token Index: 907