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

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

Neuron 705 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.9836. Min Act: -0.0000

Data Index: 978879 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 3.0436. Min Range: -3.0436

Max Act: 3.0436. Min Act: -0.0000

Data Index: 1027530 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.7898. Min Act: -0.0000

Data Index: 425829 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.7975. Min Act: -0.0000

Data Index: 168411 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.4600. Min Act: -0.0000

Data Index: 296126 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.2719. Min Act: -0.0000

Data Index: 703995 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.4591. Min Act: -0.0000

Data Index: 630965 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.3430. Min Act: -0.0000

Data Index: 117363 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.2520. Min Act: -0.0000

Data Index: 191756 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.2515. Min Act: -0.0000

Data Index: 891688 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.0534. Min Act: -0.0000

Data Index: 85787 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.0131. Min Act: -0.0000

Data Index: 747655 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.1254. Min Act: -0.0000

Data Index: 556223 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.9760. Min Act: -0.0000

Data Index: 333876 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.0489. Min Act: -0.0000

Data Index: 689171 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.1619. Min Act: -0.0000

Data Index: 152088 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.1530. Min Act: -0.0000

Data Index: 745743 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.1336. Min Act: -0.0000

Data Index: 868492 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.0098. Min Act: -0.0000

Data Index: 630458 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.9656. Min Act: -0.0000

Data Index: 455246 (C4 (Web Text))

Max Activating Token Index: 964