Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 573 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0198. Min Act: -0.0001

Data Index: 307262 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0179. Min Act: -0.0001

Data Index: 2843 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0164. Min Act: -0.0001

Data Index: 328000 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0169. Min Act: -0.0001

Data Index: 110004 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0160. Min Act: -0.0001

Data Index: 608564 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0163. Min Act: -0.0001

Data Index: 298756 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0155. Min Act: -0.0001

Data Index: 1228156 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0140. Min Act: -0.0001

Data Index: 333500 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0147. Min Act: -0.0001

Data Index: 305444 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0158. Min Act: -0.0001

Data Index: 286400 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0151. Min Act: -0.0001

Data Index: 1206042 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1507195 (Python Code)

Max Activating Token Index: 238

Text #12

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0141. Min Act: -0.0001

Data Index: 831236 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0138. Min Act: -0.0001

Data Index: 1536585 (Python Code)

Max Activating Token Index: 482

Text #14

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1057828 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0151. Min Act: -0.0001

Data Index: 433233 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0146. Min Act: -0.0001

Data Index: 1330981 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1265350 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0130. Min Act: -0.0001

Data Index: 1559408 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0135. Min Act: -0.0001

Data Index: 1502831 (Python Code)

Max Activating Token Index: 172