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

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

Neuron 1297 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.2726. Min Act: -0.0001

Data Index: 1325409 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.7941. Min Act: -0.0001

Data Index: 309069 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.2760. Min Act: -0.0001

Data Index: 1228282 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.3807. Min Act: -0.0001

Data Index: 472652 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.3577. Min Act: -0.0001

Data Index: 144967 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.2659. Min Act: -0.0000

Data Index: 561204 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.1522. Min Act: -0.0001

Data Index: 756898 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.2683. Min Act: -0.0001

Data Index: 1172069 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.1263. Min Act: -0.0001

Data Index: 1094144 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.2342. Min Act: -0.0001

Data Index: 964048 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.0959. Min Act: -0.0001

Data Index: 115780 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.0640. Min Act: -0.0001

Data Index: 1350879 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.0284. Min Act: -0.0001

Data Index: 813467 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.2140. Min Act: -0.0000

Data Index: 594636 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.0091. Min Act: -0.0001

Data Index: 260546 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.1234. Min Act: -0.0000

Data Index: 597424 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.2433. Min Act: -0.0001

Data Index: 187366 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.2333. Min Act: -0.0001

Data Index: 737344 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.1559. Min Act: -0.0001

Data Index: 625017 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 3.2726. Min Range: -3.2726

Max Act: 2.0982. Min Act: -0.0000

Data Index: 1262722 (C4 (Web Text))

Max Activating Token Index: 790