Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 181 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0005

Data Index: 1566280 (Python Code)

Max Activating Token Index: 1020

Text #1

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0154. Min Act: -0.0004

Data Index: 1428295 (Python Code)

Max Activating Token Index: 282

Text #2

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0152. Min Act: -0.0005

Data Index: 552537 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0147. Min Act: -0.0004

Data Index: 1459963 (Python Code)

Max Activating Token Index: 813

Text #4

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0146. Min Act: -0.0005

Data Index: 1277196 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0146. Min Act: -0.0004

Data Index: 1431460 (Python Code)

Max Activating Token Index: 592

Text #6

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0142. Min Act: -0.0005

Data Index: 176693 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0145. Min Act: -0.0005

Data Index: 1644896 (Python Code)

Max Activating Token Index: 569

Text #8

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0140. Min Act: -0.0004

Data Index: 1590883 (Python Code)

Max Activating Token Index: 344

Text #9

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0140. Min Act: -0.0005

Data Index: 1208080 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0141. Min Act: -0.0004

Data Index: 1586308 (Python Code)

Max Activating Token Index: 658

Text #11

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0139. Min Act: -0.0005

Data Index: 217062 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0141. Min Act: -0.0004

Data Index: 170110 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1044793 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0140. Min Act: -0.0005

Data Index: 1439766 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0136. Min Act: -0.0005

Data Index: 1105203 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0135. Min Act: -0.0005

Data Index: 336178 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0138. Min Act: -0.0005

Data Index: 1006720 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0141. Min Act: -0.0005

Data Index: 1236456 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0138. Min Act: -0.0005

Data Index: 1147920 (C4 (Web Text))

Max Activating Token Index: 209