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

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

Neuron 1890 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0151. Min Act: -0.0003

Data Index: 657582 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0158. Min Act: -0.0003

Data Index: 71705 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1073500 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1317733 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1009676 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0151. Min Act: -0.0003

Data Index: 247625 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1288532 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0132. Min Act: -0.0003

Data Index: 878513 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0147. Min Act: -0.0003

Data Index: 277293 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0133. Min Act: -0.0004

Data Index: 1144687 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0003

Data Index: 806447 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0134. Min Act: -0.0003

Data Index: 221811 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0139. Min Act: -0.0003

Data Index: 961941 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0136. Min Act: -0.0003

Data Index: 979628 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1154677 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0003

Data Index: 298859 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0004

Data Index: 567853 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0003

Data Index: 734320 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0131. Min Act: -0.0003

Data Index: 814829 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1195396 (C4 (Web Text))

Max Activating Token Index: 600