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

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

Neuron 779 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.8792. Min Range: -9.8792

Max Act: 9.8792. Min Act: -0.0000

Data Index: 1341284 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 9.8792. Min Range: -9.8792

Max Act: 9.5959. Min Act: -0.0000

Data Index: 1239641 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 9.8792. Min Range: -9.8792

Max Act: 9.3612. Min Act: -0.0000

Data Index: 339071 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 9.8792. Min Range: -9.8792

Max Act: 9.4059. Min Act: -0.0000

Data Index: 1263034 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 9.8792. Min Range: -9.8792

Max Act: 8.5758. Min Act: -0.0000

Data Index: 419707 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 9.8792. Min Range: -9.8792

Max Act: 8.7961. Min Act: -0.0000

Data Index: 82354 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 9.8792. Min Range: -9.8792

Max Act: 8.1042. Min Act: -0.0000

Data Index: 1073659 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 9.8792. Min Range: -9.8792

Max Act: 8.0268. Min Act: -0.0000

Data Index: 440387 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 9.8792. Min Range: -9.8792

Max Act: 8.2480. Min Act: -0.0000

Data Index: 1298890 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 9.8792. Min Range: -9.8792

Max Act: 7.6215. Min Act: -0.0000

Data Index: 340019 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 9.8792. Min Range: -9.8792

Max Act: 8.1791. Min Act: -0.0000

Data Index: 16968 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 9.8792. Min Range: -9.8792

Max Act: 7.6713. Min Act: -0.0000

Data Index: 903073 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 9.8792. Min Range: -9.8792

Max Act: 7.1816. Min Act: -0.0000

Data Index: 691278 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 9.8792. Min Range: -9.8792

Max Act: 7.6511. Min Act: -0.0000

Data Index: 1213327 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 9.8792. Min Range: -9.8792

Max Act: 6.9761. Min Act: -0.0000

Data Index: 483992 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 9.8792. Min Range: -9.8792

Max Act: 7.3706. Min Act: -0.0000

Data Index: 297543 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 9.8792. Min Range: -9.8792

Max Act: 7.4172. Min Act: -0.0000

Data Index: 1248130 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 9.8792. Min Range: -9.8792

Max Act: 7.6937. Min Act: -0.0000

Data Index: 1043391 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 9.8792. Min Range: -9.8792

Max Act: 6.6477. Min Act: -0.0000

Data Index: 207969 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 9.8792. Min Range: -9.8792

Max Act: 6.9267. Min Act: -0.0000

Data Index: 1162169 (C4 (Web Text))

Max Activating Token Index: 682