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

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

Neuron 1556 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1438. Min Act: -0.0000

Data Index: 888911 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1375. Min Act: -0.0000

Data Index: 836416 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1195. Min Act: -0.0000

Data Index: 695394 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1157. Min Act: -0.0000

Data Index: 720433 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1162. Min Act: -0.0000

Data Index: 601960 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1082. Min Act: -0.0000

Data Index: 750130 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1097. Min Act: -0.0000

Data Index: 630065 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1043. Min Act: -0.0000

Data Index: 830639 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1044. Min Act: -0.0000

Data Index: 446520 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1265912 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1030. Min Act: -0.0000

Data Index: 186497 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1011. Min Act: -0.0000

Data Index: 859111 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1237372 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1048. Min Act: -0.0000

Data Index: 253160 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0946. Min Act: -0.0000

Data Index: 809311 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0974. Min Act: -0.0000

Data Index: 220889 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0957. Min Act: -0.0000

Data Index: 138857 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0957. Min Act: -0.0000

Data Index: 219510 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0945. Min Act: -0.0000

Data Index: 21288 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1138747 (C4 (Web Text))

Max Activating Token Index: 985