Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 784 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0146. Min Act: -0.0002

Data Index: 137228 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0145. Min Act: -0.0002

Data Index: 532305 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0135. Min Act: -0.0002

Data Index: 791809 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0134. Min Act: -0.0002

Data Index: 92120 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0125. Min Act: -0.0002

Data Index: 452748 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0120. Min Act: -0.0002

Data Index: 379938 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0121. Min Act: -0.0002

Data Index: 702644 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0118. Min Act: -0.0002

Data Index: 197325 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1301019 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0114. Min Act: -0.0002

Data Index: 49924 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0115. Min Act: -0.0002

Data Index: 170533 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0115. Min Act: -0.0002

Data Index: 677719 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0115. Min Act: -0.0002

Data Index: 506766 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1248790 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0114. Min Act: -0.0002

Data Index: 677282 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0112. Min Act: -0.0002

Data Index: 843855 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0112. Min Act: -0.0002

Data Index: 265962 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0110. Min Act: -0.0002

Data Index: 398638 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0111. Min Act: -0.0002

Data Index: 448993 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0109. Min Act: -0.0002

Data Index: 569331 (C4 (Web Text))

Max Activating Token Index: 252