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

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

Neuron 731 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: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0004

Data Index: 1086336 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0162. Min Act: -0.0005

Data Index: 561714 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0156. Min Act: -0.0004

Data Index: 58836 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0155. Min Act: -0.0004

Data Index: 718785 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0150. Min Act: -0.0004

Data Index: 81852 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0148. Min Act: -0.0004

Data Index: 55157 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0141. Min Act: -0.0004

Data Index: 77234 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0141. Min Act: -0.0004

Data Index: 426878 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0138. Min Act: -0.0004

Data Index: 834813 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0137. Min Act: -0.0004

Data Index: 839871 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0137. Min Act: -0.0004

Data Index: 983077 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0137. Min Act: -0.0004

Data Index: 928492 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0136. Min Act: -0.0004

Data Index: 1111982 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0134. Min Act: -0.0004

Data Index: 410596 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0136. Min Act: -0.0004

Data Index: 778200 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0132. Min Act: -0.0004

Data Index: 1031793 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0131. Min Act: -0.0004

Data Index: 174549 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0128. Min Act: -0.0004

Data Index: 386797 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0129. Min Act: -0.0004

Data Index: 17531 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0129. Min Act: -0.0004

Data Index: 749749 (C4 (Web Text))

Max Activating Token Index: 345