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

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

Neuron 4328 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1130. Min Range: -4.1130

Max Act: 4.1130. Min Act: -0.0000

Data Index: 436390 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.9122. Min Act: -0.0000

Data Index: 912936 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.9201. Min Act: -0.0000

Data Index: 376196 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.8855. Min Act: -0.0000

Data Index: 1351174 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.7178. Min Act: -0.0000

Data Index: 838889 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.5692. Min Act: -0.0000

Data Index: 560377 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.3976. Min Act: -0.0000

Data Index: 595958 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.5382. Min Act: -0.0000

Data Index: 233993 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.1455. Min Act: -0.0000

Data Index: 620223 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 4.1130. Min Range: -4.1130

Max Act: 2.9367. Min Act: -0.0000

Data Index: 106328 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 4.1130. Min Range: -4.1130

Max Act: 2.9534. Min Act: -0.0000

Data Index: 1119418 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 4.1130. Min Range: -4.1130

Max Act: 2.9679. Min Act: -0.0000

Data Index: 1276939 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.0593. Min Act: -0.0000

Data Index: 556696 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 4.1130. Min Range: -4.1130

Max Act: 2.9056. Min Act: -0.0000

Data Index: 1204341 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.0469. Min Act: -0.0000

Data Index: 323564 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 4.1130. Min Range: -4.1130

Max Act: 2.8948. Min Act: -0.0000

Data Index: 262210 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 4.1130. Min Range: -4.1130

Max Act: 3.1973. Min Act: -0.0000

Data Index: 212783 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 4.1130. Min Range: -4.1130

Max Act: 2.9524. Min Act: -0.0000

Data Index: 452096 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 4.1130. Min Range: -4.1130

Max Act: 2.9823. Min Act: -0.0000

Data Index: 1024094 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 4.1130. Min Range: -4.1130

Max Act: 2.9743. Min Act: -0.0000

Data Index: 131093 (C4 (Web Text))

Max Activating Token Index: 335