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

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

Neuron 5313 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1179. Min Range: -1.1179

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1446852 (Python Code)

Max Activating Token Index: 366

Text #1

Max Range: 1.1179. Min Range: -1.1179

Max Act: 1.0726. Min Act: -0.0001

Data Index: 1415783 (Python Code)

Max Activating Token Index: 356

Text #2

Max Range: 1.1179. Min Range: -1.1179

Max Act: 1.0176. Min Act: -0.0000

Data Index: 26448 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1546749 (Python Code)

Max Activating Token Index: 914

Text #4

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9051. Min Act: -0.0000

Data Index: 733855 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9247. Min Act: -0.0001

Data Index: 1382547 (Python Code)

Max Activating Token Index: 192

Text #6

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1588448 (Python Code)

Max Activating Token Index: 557

Text #7

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1398398 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8797. Min Act: -0.0000

Data Index: 575638 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8768. Min Act: -0.0000

Data Index: 772202 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9482. Min Act: -0.0000

Data Index: 151712 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9073. Min Act: -0.0000

Data Index: 477491 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9159. Min Act: -0.0001

Data Index: 1355522 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1608250 (Python Code)

Max Activating Token Index: 141

Text #14

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8920. Min Act: -0.0001

Data Index: 1408740 (Python Code)

Max Activating Token Index: 314

Text #15

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8613. Min Act: -0.0001

Data Index: 1597558 (Python Code)

Max Activating Token Index: 277

Text #16

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8971. Min Act: -0.0001

Data Index: 1485281 (Python Code)

Max Activating Token Index: 193

Text #17

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8172. Min Act: -0.0001

Data Index: 1465441 (Python Code)

Max Activating Token Index: 1012

Text #18

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7399. Min Act: -0.0000

Data Index: 121114 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1157961 (C4 (Web Text))

Max Activating Token Index: 391