Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4221 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.4494. Min Act: -0.0000

Data Index: 817784 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.2140. Min Act: -0.0000

Data Index: 947415 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1245938 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.9048. Min Act: -0.0000

Data Index: 282264 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.9354. Min Act: -0.0000

Data Index: 364651 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.8282. Min Act: -0.0000

Data Index: 930909 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.8059. Min Act: 0.0000

Data Index: 299478 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.8279. Min Act: -0.0000

Data Index: 643692 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.7732. Min Act: -0.0000

Data Index: 977544 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.7760. Min Act: -0.0000

Data Index: 566594 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1239640 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.7672. Min Act: -0.0000

Data Index: 208005 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.7241. Min Act: 0.0000

Data Index: 788477 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.7421. Min Act: -0.0000

Data Index: 857871 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.7068. Min Act: -0.0000

Data Index: 121217 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1143562 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1030703 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1196837 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.6602. Min Act: 0.0000

Data Index: 1299557 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.6513. Min Act: -0.0000

Data Index: 99901 (C4 (Web Text))

Max Activating Token Index: 457