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

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

Neuron 5642 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8718. Min Range: -5.8718

Max Act: 5.7349. Min Act: -0.0001

Data Index: 498634 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 5.8718. Min Range: -5.8718

Max Act: 5.8718. Min Act: -0.0001

Data Index: 671423 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 5.8718. Min Range: -5.8718

Max Act: 5.4936. Min Act: -0.0001

Data Index: 141219 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 5.8718. Min Range: -5.8718

Max Act: 5.8037. Min Act: -0.0001

Data Index: 50747 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 5.8718. Min Range: -5.8718

Max Act: 5.7630. Min Act: -0.0001

Data Index: 79883 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 5.8718. Min Range: -5.8718

Max Act: 5.6313. Min Act: -0.0001

Data Index: 452685 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 5.8718. Min Range: -5.8718

Max Act: 5.2286. Min Act: -0.0001

Data Index: 54448 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 5.8718. Min Range: -5.8718

Max Act: 5.0625. Min Act: -0.0001

Data Index: 500163 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 5.8718. Min Range: -5.8718

Max Act: 5.2351. Min Act: -0.0001

Data Index: 1018115 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 5.8718. Min Range: -5.8718

Max Act: 4.7394. Min Act: -0.0001

Data Index: 689795 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 5.8718. Min Range: -5.8718

Max Act: 4.7597. Min Act: -0.0001

Data Index: 1354912 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 5.8718. Min Range: -5.8718

Max Act: 4.7822. Min Act: -0.0001

Data Index: 393695 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 5.8718. Min Range: -5.8718

Max Act: 4.7868. Min Act: -0.0001

Data Index: 418093 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 5.8718. Min Range: -5.8718

Max Act: 5.1324. Min Act: -0.0001

Data Index: 300210 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 5.8718. Min Range: -5.8718

Max Act: 4.8526. Min Act: -0.0001

Data Index: 973206 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 5.8718. Min Range: -5.8718

Max Act: 4.4562. Min Act: -0.0001

Data Index: 722154 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 5.8718. Min Range: -5.8718

Max Act: 4.0906. Min Act: -0.0001

Data Index: 1011996 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 5.8718. Min Range: -5.8718

Max Act: 4.7873. Min Act: -0.0001

Data Index: 1040368 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 5.8718. Min Range: -5.8718

Max Act: 4.5973. Min Act: -0.0001

Data Index: 117068 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 5.8718. Min Range: -5.8718

Max Act: 4.2331. Min Act: -0.0001

Data Index: 306034 (C4 (Web Text))

Max Activating Token Index: 803