Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 542 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2859. Min Act: -0.0002

Data Index: 79081 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2675. Min Act: -0.0002

Data Index: 391018 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2682. Min Act: -0.0001

Data Index: 1330006 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2792. Min Act: -0.0002

Data Index: 1272750 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2443. Min Act: -0.0002

Data Index: 186529 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2660. Min Act: -0.0002

Data Index: 625588 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2508. Min Act: -0.0002

Data Index: 78142 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2640. Min Act: -0.0002

Data Index: 572253 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2693. Min Act: -0.0002

Data Index: 1106084 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2729. Min Act: -0.0002

Data Index: 728955 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2474. Min Act: -0.0002

Data Index: 407327 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2648. Min Act: -0.0002

Data Index: 1257332 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2631. Min Act: -0.0002

Data Index: 1326346 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2554. Min Act: -0.0002

Data Index: 241619 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2790. Min Act: -0.0002

Data Index: 414436 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2166. Min Act: -0.0002

Data Index: 462613 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2800. Min Act: -0.0002

Data Index: 1254939 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2624. Min Act: -0.0002

Data Index: 147134 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2590. Min Act: -0.0002

Data Index: 363665 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2414. Min Act: -0.0002

Data Index: 759179 (C4 (Web Text))

Max Activating Token Index: 786