Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 177 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0151. Min Act: -0.0006

Data Index: 478818 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0147. Min Act: -0.0006

Data Index: 15195 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0143. Min Act: -0.0005

Data Index: 276647 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0145. Min Act: -0.0006

Data Index: 42553 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0144. Min Act: -0.0006

Data Index: 869889 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0143. Min Act: -0.0006

Data Index: 228509 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0141. Min Act: -0.0006

Data Index: 955103 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1471672 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0140. Min Act: -0.0006

Data Index: 441566 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0141. Min Act: -0.0006

Data Index: 772682 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1221630 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1437903 (Python Code)

Max Activating Token Index: 1007

Text #12

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1532141 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0136. Min Act: -0.0005

Data Index: 1634208 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0136. Min Act: -0.0005

Data Index: 687295 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0135. Min Act: -0.0005

Data Index: 864880 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0135. Min Act: -0.0006

Data Index: 117043 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1319925 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1241269 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0132. Min Act: -0.0006

Data Index: 90797 (C4 (Web Text))

Max Activating Token Index: 587