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

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

Neuron 1997 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: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0006

Data Index: 847444 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1301560 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1317212 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1122126 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1104741 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0130. Min Act: -0.0006

Data Index: 15886 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0130. Min Act: -0.0006

Data Index: 946765 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0129. Min Act: -0.0006

Data Index: 723050 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1080367 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0128. Min Act: -0.0006

Data Index: 696864 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1068168 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0127. Min Act: -0.0006

Data Index: 579205 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0127. Min Act: -0.0006

Data Index: 765793 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0126. Min Act: -0.0006

Data Index: 966204 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0126. Min Act: -0.0006

Data Index: 822985 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0126. Min Act: -0.0006

Data Index: 368927 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0128. Min Act: -0.0006

Data Index: 983880 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0122. Min Act: -0.0006

Data Index: 234239 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0125. Min Act: -0.0006

Data Index: 526420 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1312943 (C4 (Web Text))

Max Activating Token Index: 754