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

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

Neuron 4686 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: 1.8577. Min Range: -1.8577

Max Act: 1.8577. Min Act: -0.0000

Data Index: 50853 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.6575. Min Act: -0.0000

Data Index: 506772 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.8019. Min Act: -0.0000

Data Index: 365256 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4815. Min Act: -0.0000

Data Index: 209162 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4423. Min Act: -0.0000

Data Index: 1316089 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4797. Min Act: -0.0000

Data Index: 570757 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3818. Min Act: -0.0000

Data Index: 929601 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3685. Min Act: -0.0000

Data Index: 1042056 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4082. Min Act: -0.0000

Data Index: 978532 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3521. Min Act: -0.0000

Data Index: 1566707 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.5443. Min Act: -0.0000

Data Index: 987639 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3802. Min Act: -0.0000

Data Index: 364826 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3959. Min Act: -0.0000

Data Index: 71988 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1252741 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3233. Min Act: -0.0000

Data Index: 275780 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3170. Min Act: -0.0000

Data Index: 417830 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3708. Min Act: -0.0000

Data Index: 811262 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3184. Min Act: -0.0000

Data Index: 955870 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2899. Min Act: -0.0000

Data Index: 853511 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2447. Min Act: -0.0000

Data Index: 575538 (C4 (Web Text))

Max Activating Token Index: 149