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

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

Neuron 853 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: 0.0175. Min Range: -0.0175

Max Act: 0.0175. Min Act: -0.0006

Data Index: 634203 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0160. Min Act: -0.0006

Data Index: 870153 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0153. Min Act: -0.0006

Data Index: 98893 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0159. Min Act: -0.0006

Data Index: 641696 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1219680 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0148. Min Act: -0.0006

Data Index: 229912 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1311047 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0153. Min Act: -0.0006

Data Index: 963533 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0149. Min Act: -0.0006

Data Index: 823251 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0149. Min Act: -0.0006

Data Index: 74760 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0144. Min Act: -0.0006

Data Index: 737144 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0143. Min Act: -0.0006

Data Index: 95949 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0142. Min Act: -0.0006

Data Index: 222719 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0141. Min Act: -0.0006

Data Index: 611526 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0141. Min Act: -0.0006

Data Index: 484280 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0138. Min Act: -0.0006

Data Index: 797585 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0137. Min Act: -0.0006

Data Index: 923738 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0136. Min Act: -0.0006

Data Index: 932552 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0132. Min Act: -0.0006

Data Index: 669288 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0134. Min Act: -0.0006

Data Index: 706080 (C4 (Web Text))

Max Activating Token Index: 908