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

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

Neuron 1725 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1350. Min Act: -0.0006

Data Index: 1243489 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1254. Min Act: -0.0006

Data Index: 300349 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1203. Min Act: -0.0006

Data Index: 877019 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1185. Min Act: -0.0006

Data Index: 1161407 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1145. Min Act: -0.0006

Data Index: 570242 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1129. Min Act: -0.0006

Data Index: 109593 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1144. Min Act: -0.0005

Data Index: 135878 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1097. Min Act: -0.0006

Data Index: 1238072 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1138. Min Act: -0.0006

Data Index: 726264 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1155. Min Act: -0.0006

Data Index: 832046 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1129. Min Act: -0.0006

Data Index: 1376589 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1161. Min Act: -0.0006

Data Index: 1124293 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1083. Min Act: -0.0006

Data Index: 1043329 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1042. Min Act: -0.0006

Data Index: 735496 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1078. Min Act: -0.0006

Data Index: 37182 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1052. Min Act: -0.0006

Data Index: 288971 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1091. Min Act: -0.0006

Data Index: 51788 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1088. Min Act: -0.0006

Data Index: 162389 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1086. Min Act: -0.0006

Data Index: 67339 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1104. Min Act: -0.0006

Data Index: 591001 (C4 (Web Text))

Max Activating Token Index: 791