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

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

Neuron 3546 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1133733 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1263844 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1185353 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.6342. Min Act: -0.0000

Data Index: 884972 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1449199 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5883. Min Act: -0.0000

Data Index: 646487 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1051366 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1005355 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1073162 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1079538 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5660. Min Act: -0.0000

Data Index: 548832 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1246524 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5314. Min Act: -0.0000

Data Index: 485049 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4968. Min Act: -0.0000

Data Index: 728229 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4871. Min Act: -0.0000

Data Index: 688088 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1134750 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5053. Min Act: 0.0000

Data Index: 162367 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1236058 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5004. Min Act: -0.0000

Data Index: 293952 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5033. Min Act: -0.0000

Data Index: 143839 (C4 (Web Text))

Max Activating Token Index: 1021