Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 210 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0176. Min Act: -0.0002

Data Index: 707590 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0163. Min Act: -0.0002

Data Index: 991038 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0161. Min Act: -0.0002

Data Index: 570688 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0157. Min Act: -0.0002

Data Index: 104967 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0147. Min Act: -0.0002

Data Index: 125052 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0146. Min Act: -0.0002

Data Index: 52625 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1285471 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0143. Min Act: -0.0002

Data Index: 157011 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0143. Min Act: -0.0002

Data Index: 842723 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0142. Min Act: -0.0002

Data Index: 613310 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0143. Min Act: -0.0002

Data Index: 713577 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0143. Min Act: -0.0002

Data Index: 525281 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0141. Min Act: -0.0002

Data Index: 801810 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0141. Min Act: -0.0002

Data Index: 719365 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1046116 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0140. Min Act: -0.0003

Data Index: 427209 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1322993 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1356183 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1025048 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1216710 (C4 (Web Text))

Max Activating Token Index: 999