Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3340 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7943. Min Act: -0.0000

Data Index: 861832 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7929. Min Act: -0.0000

Data Index: 262158 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7884. Min Act: -0.0000

Data Index: 608247 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1268135 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1277974 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1101428 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7047. Min Act: -0.0000

Data Index: 54485 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6686. Min Act: -0.0000

Data Index: 73576 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1000932 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6293. Min Act: -0.0000

Data Index: 745322 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6920. Min Act: -0.0000

Data Index: 304220 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6840. Min Act: -0.0000

Data Index: 531356 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6738. Min Act: -0.0000

Data Index: 868602 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6548. Min Act: -0.0000

Data Index: 255523 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7145. Min Act: -0.0000

Data Index: 48155 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1087373 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1248906 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6700. Min Act: -0.0000

Data Index: 979497 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6898. Min Act: -0.0000

Data Index: 937862 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6923. Min Act: -0.0000

Data Index: 287700 (C4 (Web Text))

Max Activating Token Index: 188