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

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

Neuron 1947 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: 0.0158. Min Range: -0.0158

Max Act: 0.0158. Min Act: -0.0004

Data Index: 1460591 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0139. Min Act: -0.0004

Data Index: 632529 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: -0.0004

Data Index: 546995 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: -0.0004

Data Index: 192884 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0143. Min Act: -0.0004

Data Index: 74565 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0142. Min Act: -0.0004

Data Index: 479791 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0139. Min Act: -0.0005

Data Index: 852977 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1188615 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0132. Min Act: -0.0004

Data Index: 209008 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0128. Min Act: -0.0004

Data Index: 283360 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0133. Min Act: -0.0004

Data Index: 637794 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0130. Min Act: -0.0005

Data Index: 822665 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0130. Min Act: -0.0004

Data Index: 1322014 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0132. Min Act: -0.0004

Data Index: 55367 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0130. Min Act: -0.0004

Data Index: 94961 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0132. Min Act: -0.0004

Data Index: 1408922 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0129. Min Act: -0.0004

Data Index: 1558538 (Python Code)

Max Activating Token Index: 433

Text #17

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0131. Min Act: -0.0004

Data Index: 1509956 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0125. Min Act: -0.0004

Data Index: 509033 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0130. Min Act: -0.0004

Data Index: 603917 (C4 (Web Text))

Max Activating Token Index: 845