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

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

Neuron 3683 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.9317. Min Act: -0.0000

Data Index: 1248333 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.8681. Min Act: -0.0000

Data Index: 1076749 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.5477. Min Act: -0.0000

Data Index: 1284268 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.4583. Min Act: -0.0000

Data Index: 76515 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.5308. Min Act: -0.0000

Data Index: 717335 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.4628. Min Act: -0.0000

Data Index: 1299979 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.3835. Min Act: -0.0000

Data Index: 638844 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.3142. Min Act: -0.0000

Data Index: 1050380 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.3930. Min Act: -0.0000

Data Index: 1268135 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1259605 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.2891. Min Act: -0.0000

Data Index: 756854 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.3666. Min Act: -0.0000

Data Index: 235453 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.4443. Min Act: -0.0000

Data Index: 490583 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.4475. Min Act: -0.0000

Data Index: 319684 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.4295. Min Act: -0.0000

Data Index: 606399 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.3446. Min Act: -0.0000

Data Index: 631642 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.2556. Min Act: -0.0000

Data Index: 282020 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.2328. Min Act: -0.0000

Data Index: 1226014 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.3019. Min Act: -0.0000

Data Index: 1356486 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 1.9317. Min Range: -1.9317

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1091728 (C4 (Web Text))

Max Activating Token Index: 549