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

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

Neuron 5157 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7679. Min Range: -2.7679

Max Act: 2.7679. Min Act: -0.0000

Data Index: 211250 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 2.7679. Min Range: -2.7679

Max Act: 2.7279. Min Act: -0.0000

Data Index: 989499 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 2.7679. Min Range: -2.7679

Max Act: 2.4036. Min Act: -0.0000

Data Index: 1216634 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 2.7679. Min Range: -2.7679

Max Act: 2.2548. Min Act: -0.0000

Data Index: 848414 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.9421. Min Act: -0.0000

Data Index: 382566 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.9127. Min Act: -0.0000

Data Index: 644152 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.8846. Min Act: -0.0000

Data Index: 457210 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.8122. Min Act: -0.0000

Data Index: 874445 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.8113. Min Act: -0.0000

Data Index: 932845 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.7271. Min Act: -0.0000

Data Index: 674829 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.5686. Min Act: -0.0000

Data Index: 1288123 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.5557. Min Act: -0.0000

Data Index: 144385 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.6481. Min Act: -0.0000

Data Index: 921442 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.6641. Min Act: -0.0000

Data Index: 402130 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.6589. Min Act: -0.0000

Data Index: 323452 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.7449. Min Act: 0.0000

Data Index: 346186 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.7399. Min Act: -0.0000

Data Index: 1344908 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.5397. Min Act: -0.0000

Data Index: 649489 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.7321. Min Act: -0.0000

Data Index: 1196858 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 2.7679. Min Range: -2.7679

Max Act: 1.6193. Min Act: -0.0000

Data Index: 33089 (C4 (Web Text))

Max Activating Token Index: 610