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

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

Neuron 4535 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: 2.8075. Min Range: -2.8075

Max Act: 2.8075. Min Act: -0.0000

Data Index: 1164488 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 2.8075. Min Range: -2.8075

Max Act: 2.3745. Min Act: -0.0001

Data Index: 564099 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 2.8075. Min Range: -2.8075

Max Act: 2.3750. Min Act: -0.0001

Data Index: 533890 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 2.8075. Min Range: -2.8075

Max Act: 2.1616. Min Act: -0.0001

Data Index: 682505 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 2.8075. Min Range: -2.8075

Max Act: 2.0163. Min Act: -0.0000

Data Index: 147127 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 2.8075. Min Range: -2.8075

Max Act: 2.0172. Min Act: -0.0000

Data Index: 883213 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 2.8075. Min Range: -2.8075

Max Act: 2.1258. Min Act: -0.0001

Data Index: 1224525 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.8851. Min Act: -0.0000

Data Index: 588770 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.6887. Min Act: -0.0000

Data Index: 209570 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.5893. Min Act: -0.0001

Data Index: 415609 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.5798. Min Act: -0.0001

Data Index: 1025693 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.5492. Min Act: -0.0000

Data Index: 764325 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 2.8075. Min Range: -2.8075

Max Act: 2.0335. Min Act: -0.0001

Data Index: 1332024 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.6154. Min Act: -0.0000

Data Index: 325496 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.4732. Min Act: -0.0001

Data Index: 1128574 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.4631. Min Act: -0.0001

Data Index: 571338 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.4393. Min Act: -0.0001

Data Index: 618499 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.3469. Min Act: -0.0000

Data Index: 1175327 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.2733. Min Act: -0.0001

Data Index: 583862 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 2.8075. Min Range: -2.8075

Max Act: 1.5762. Min Act: -0.0000

Data Index: 1136275 (C4 (Web Text))

Max Activating Token Index: 195