Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2315 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.1639. Min Act: -0.0001

Data Index: 538090 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0340. Min Act: -0.0001

Data Index: 402830 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0625. Min Act: -0.0001

Data Index: 722306 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0312. Min Act: -0.0001

Data Index: 827655 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0211. Min Act: -0.0001

Data Index: 462746 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0225. Min Act: -0.0001

Data Index: 602680 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8642. Min Act: -0.0001

Data Index: 349327 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9915. Min Act: -0.0001

Data Index: 860040 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9556. Min Act: -0.0001

Data Index: 1285808 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9557. Min Act: -0.0001

Data Index: 1002733 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9291. Min Act: -0.0001

Data Index: 98660 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8355. Min Act: -0.0001

Data Index: 769343 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9090. Min Act: -0.0001

Data Index: 1163336 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9421. Min Act: -0.0001

Data Index: 56746 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8997. Min Act: -0.0001

Data Index: 979697 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9019. Min Act: -0.0001

Data Index: 74377 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9342. Min Act: -0.0001

Data Index: 788339 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8577. Min Act: -0.0001

Data Index: 953218 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.8841. Min Act: -0.0001

Data Index: 704814 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9096. Min Act: -0.0001

Data Index: 126354 (C4 (Web Text))

Max Activating Token Index: 965