Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 100 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0165. Min Act: -0.0004

Data Index: 1062480 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0162. Min Act: -0.0004

Data Index: 482315 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0154. Min Act: -0.0004

Data Index: 705685 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0155. Min Act: -0.0004

Data Index: 293789 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0154. Min Act: -0.0004

Data Index: 750485 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0155. Min Act: -0.0004

Data Index: 103464 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0152. Min Act: -0.0004

Data Index: 724351 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0151. Min Act: -0.0005

Data Index: 1341851 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0150. Min Act: -0.0004

Data Index: 300911 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0150. Min Act: -0.0004

Data Index: 1238226 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0147. Min Act: -0.0004

Data Index: 1346556 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0148. Min Act: -0.0005

Data Index: 149596 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0148. Min Act: -0.0004

Data Index: 737905 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0148. Min Act: -0.0004

Data Index: 390172 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0148. Min Act: -0.0004

Data Index: 1276756 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0147. Min Act: -0.0004

Data Index: 1237569 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0146. Min Act: -0.0004

Data Index: 703661 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0146. Min Act: -0.0005

Data Index: 306298 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0144. Min Act: -0.0004

Data Index: 51997 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0143. Min Act: -0.0005

Data Index: 88555 (C4 (Web Text))

Max Activating Token Index: 898