Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3055 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0175. Min Act: -0.0004

Data Index: 159849 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0168. Min Act: -0.0004

Data Index: 847809 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0163. Min Act: -0.0004

Data Index: 1148989 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0156. Min Act: -0.0004

Data Index: 873325 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0152. Min Act: -0.0004

Data Index: 1068544 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0137. Min Act: -0.0004

Data Index: 886827 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0147. Min Act: -0.0004

Data Index: 158450 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0147. Min Act: -0.0004

Data Index: 433350 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0146. Min Act: -0.0004

Data Index: 1339746 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0146. Min Act: -0.0004

Data Index: 1147274 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0144. Min Act: -0.0004

Data Index: 860211 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0137. Min Act: -0.0004

Data Index: 541593 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0143. Min Act: -0.0004

Data Index: 43178 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0143. Min Act: -0.0004

Data Index: 87855 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0132. Min Act: -0.0004

Data Index: 484772 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0131. Min Act: -0.0004

Data Index: 1002964 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0130. Min Act: -0.0004

Data Index: 686661 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0130. Min Act: -0.0004

Data Index: 801621 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0123. Min Act: -0.0004

Data Index: 1088299 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0126. Min Act: -0.0004

Data Index: 343524 (C4 (Web Text))

Max Activating Token Index: 823