Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 953 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.5137. Min Act: -0.0001

Data Index: 1256329 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.5154. Min Act: -0.0001

Data Index: 83595 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.3515. Min Act: -0.0001

Data Index: 901224 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.3928. Min Act: -0.0001

Data Index: 1119625 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.4625. Min Act: -0.0001

Data Index: 615287 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.4267. Min Act: -0.0001

Data Index: 947689 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.3571. Min Act: -0.0001

Data Index: 410529 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.3318. Min Act: -0.0001

Data Index: 19337 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.4254. Min Act: -0.0001

Data Index: 492290 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.3359. Min Act: -0.0001

Data Index: 658835 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1824. Min Act: -0.0001

Data Index: 83870 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.2304. Min Act: -0.0001

Data Index: 1300584 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1960. Min Act: -0.0001

Data Index: 961945 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.3497. Min Act: -0.0001

Data Index: 289025 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1700. Min Act: -0.0001

Data Index: 1311499 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1765. Min Act: -0.0001

Data Index: 430542 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1686. Min Act: -0.0001

Data Index: 602704 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1076. Min Act: -0.0001

Data Index: 563823 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.0305. Min Act: -0.0001

Data Index: 282735 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1195. Min Act: -0.0001

Data Index: 492776 (C4 (Web Text))

Max Activating Token Index: 105