Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4051 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.6780. Min Act: -0.0000

Data Index: 595617 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.5678. Min Act: -0.0000

Data Index: 405874 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1395. Min Act: -0.0000

Data Index: 547478 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.5171. Min Act: -0.0000

Data Index: 1015638 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.6263. Min Act: -0.0000

Data Index: 932705 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.3974. Min Act: -0.0000

Data Index: 1146883 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.4939. Min Act: -0.0000

Data Index: 630476 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.4401. Min Act: -0.0000

Data Index: 515569 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.3178. Min Act: -0.0000

Data Index: 1112022 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.4237. Min Act: -0.0000

Data Index: 403826 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1742. Min Act: -0.0000

Data Index: 425821 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.3423. Min Act: -0.0000

Data Index: 1275449 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.3364. Min Act: -0.0000

Data Index: 237069 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.0763. Min Act: -0.0000

Data Index: 250493 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.2946. Min Act: -0.0000

Data Index: 885733 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.3892. Min Act: -0.0000

Data Index: 571253 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.4835. Min Act: -0.0000

Data Index: 628834 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1907. Min Act: -0.0000

Data Index: 379323 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1824. Min Act: -0.0000

Data Index: 30581 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1871. Min Act: -0.0000

Data Index: 54142 (C4 (Web Text))

Max Activating Token Index: 220