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

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

Neuron 3238 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.5943. Min Act: -0.0001

Data Index: 592446 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.5034. Min Act: -0.0000

Data Index: 95153 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.5174. Min Act: -0.0001

Data Index: 153381 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4813. Min Act: -0.0001

Data Index: 1226309 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4880. Min Act: -0.0001

Data Index: 333337 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4685. Min Act: -0.0001

Data Index: 444178 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4175. Min Act: -0.0001

Data Index: 1169589 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4217. Min Act: -0.0001

Data Index: 1530722 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4008. Min Act: -0.0001

Data Index: 444618 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4255. Min Act: -0.0001

Data Index: 96729 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3766. Min Act: -0.0000

Data Index: 549093 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4020. Min Act: -0.0001

Data Index: 1032592 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3728. Min Act: -0.0001

Data Index: 64843 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3816. Min Act: -0.0001

Data Index: 1050927 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3508. Min Act: -0.0001

Data Index: 1049680 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3415. Min Act: -0.0000

Data Index: 627567 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3356. Min Act: -0.0001

Data Index: 1600274 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3080. Min Act: -0.0001

Data Index: 1243886 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.2959. Min Act: -0.0001

Data Index: 1199450 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.2937. Min Act: -0.0001

Data Index: 918750 (C4 (Web Text))

Max Activating Token Index: 680