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

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

Neuron 128 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: 0.0138. Min Range: -0.0138

Max Act: 0.0136. Min Act: -0.0002

Data Index: 541320 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0002

Data Index: 264612 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0136. Min Act: -0.0002

Data Index: 640275 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1192309 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1078140 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0002

Data Index: 714233 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0134. Min Act: -0.0002

Data Index: 868153 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0002

Data Index: 563148 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0002

Data Index: 196909 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0002

Data Index: 637140 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1070421 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0002

Data Index: 362134 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1357217 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0002

Data Index: 623913 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0129. Min Act: -0.0002

Data Index: 606521 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1313131 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0002

Data Index: 347540 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1101838 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0128. Min Act: -0.0002

Data Index: 724716 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1157633 (C4 (Web Text))

Max Activating Token Index: 81