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

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

Neuron 3852 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: 1.3536. Min Range: -1.3536

Max Act: 1.3536. Min Act: -0.0000

Data Index: 280167 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2643. Min Act: -0.0000

Data Index: 392773 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2674. Min Act: -0.0000

Data Index: 854248 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2982. Min Act: -0.0000

Data Index: 474953 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2102. Min Act: -0.0000

Data Index: 714792 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1940. Min Act: -0.0000

Data Index: 1313728 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1245. Min Act: -0.0000

Data Index: 461557 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2581. Min Act: -0.0000

Data Index: 772 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0713. Min Act: -0.0000

Data Index: 539525 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1660. Min Act: -0.0000

Data Index: 962906 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1702. Min Act: -0.0000

Data Index: 1471249 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1289. Min Act: -0.0000

Data Index: 148771 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1550. Min Act: -0.0000

Data Index: 883774 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1843. Min Act: -0.0000

Data Index: 217423 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1322. Min Act: -0.0000

Data Index: 45107 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0497. Min Act: -0.0000

Data Index: 943946 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0872. Min Act: -0.0000

Data Index: 93569 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0739. Min Act: -0.0000

Data Index: 478550 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0623. Min Act: -0.0000

Data Index: 267279 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0667. Min Act: -0.0000

Data Index: 819289 (C4 (Web Text))

Max Activating Token Index: 513