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

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

Neuron 3782 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5876. Min Act: -0.0000

Data Index: 821927 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1283702 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1314859 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5607. Min Act: -0.0000

Data Index: 197676 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5518. Min Act: -0.0000

Data Index: 732472 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5586. Min Act: 0.0000

Data Index: 407494 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4980. Min Act: -0.0000

Data Index: 545860 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5573. Min Act: -0.0000

Data Index: 217493 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4980. Min Act: -0.0000

Data Index: 210757 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5084. Min Act: -0.0000

Data Index: 829527 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4777. Min Act: -0.0000

Data Index: 861408 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5082. Min Act: -0.0000

Data Index: 623595 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1238293 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4580. Min Act: -0.0000

Data Index: 583011 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4910. Min Act: -0.0000

Data Index: 428051 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5032. Min Act: -0.0000

Data Index: 633775 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4861. Min Act: -0.0000

Data Index: 887196 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1285927 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4812. Min Act: -0.0000

Data Index: 982948 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4820. Min Act: -0.0000

Data Index: 447945 (C4 (Web Text))

Max Activating Token Index: 529