Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 737 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0001

Data Index: 393719 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1360535 (Python Code)

Max Activating Token Index: 388

Text #2

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0156. Min Act: -0.0001

Data Index: 277372 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0166. Min Act: -0.0001

Data Index: 262066 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0132. Min Act: -0.0001

Data Index: 1605673 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1519844 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1240590 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0153. Min Act: -0.0001

Data Index: 373939 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1026253 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0150. Min Act: -0.0001

Data Index: 317056 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0148. Min Act: -0.0001

Data Index: 256898 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0111. Min Act: -0.0001

Data Index: 883693 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0157. Min Act: -0.0001

Data Index: 100183 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0137. Min Act: -0.0001

Data Index: 400267 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0136. Min Act: -0.0001

Data Index: 1580633 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0152. Min Act: -0.0001

Data Index: 186932 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0145. Min Act: -0.0001

Data Index: 426581 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0140. Min Act: -0.0001

Data Index: 296348 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0139. Min Act: -0.0001

Data Index: 939833 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0144. Min Act: -0.0001

Data Index: 69897 (C4 (Web Text))

Max Activating Token Index: 145