Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4595 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1614. Min Act: -0.0002

Data Index: 748499 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1590. Min Act: -0.0002

Data Index: 449428 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1559. Min Act: -0.0002

Data Index: 283943 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1449. Min Act: -0.0002

Data Index: 59058 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1416. Min Act: -0.0002

Data Index: 686482 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1430. Min Act: -0.0002

Data Index: 931906 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1344. Min Act: -0.0002

Data Index: 1454172 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1285. Min Act: -0.0002

Data Index: 314085 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1264. Min Act: -0.0002

Data Index: 452669 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1125. Min Act: -0.0002

Data Index: 911944 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1172. Min Act: -0.0002

Data Index: 294237 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1155. Min Act: -0.0002

Data Index: 98256 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1047. Min Act: -0.0002

Data Index: 242719 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1088. Min Act: -0.0002

Data Index: 849863 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1140. Min Act: -0.0002

Data Index: 358044 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1077. Min Act: -0.0002

Data Index: 418741 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1071. Min Act: -0.0002

Data Index: 109244 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1076. Min Act: -0.0002

Data Index: 1642890 (Python Code)

Max Activating Token Index: 185

Text #18

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1063. Min Act: -0.0002

Data Index: 67458 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1062. Min Act: -0.0002

Data Index: 220605 (C4 (Web Text))

Max Activating Token Index: 726