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

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

Neuron 3503 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0507. Min Range: -1.0507

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1328459 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 1.0507. Min Range: -1.0507

Max Act: 1.0411. Min Act: -0.0000

Data Index: 126049 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1259844 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 1.0507. Min Range: -1.0507

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1336674 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.0507. Min Range: -1.0507

Max Act: 1.0478. Min Act: -0.0000

Data Index: 667085 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9096. Min Act: -0.0000

Data Index: 34852 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1189166 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9141. Min Act: -0.0000

Data Index: 280259 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9246. Min Act: -0.0000

Data Index: 111657 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8802. Min Act: -0.0000

Data Index: 301855 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8815. Min Act: -0.0000

Data Index: 257553 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9539. Min Act: -0.0000

Data Index: 217016 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1284757 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1352234 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8968. Min Act: -0.0000

Data Index: 427964 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1350483 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8630. Min Act: -0.0000

Data Index: 866509 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9409. Min Act: -0.0000

Data Index: 517621 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1263256 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1136461 (C4 (Web Text))

Max Activating Token Index: 635