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

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

Neuron 1554 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2399. Min Range: -2.2399

Max Act: 2.2399. Min Act: -0.0000

Data Index: 997810 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 2.2399. Min Range: -2.2399

Max Act: 2.1907. Min Act: -0.0000

Data Index: 224167 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 2.2399. Min Range: -2.2399

Max Act: 2.1078. Min Act: -0.0000

Data Index: 246502 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.7748. Min Act: -0.0000

Data Index: 597640 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.5770. Min Act: -0.0000

Data Index: 591182 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.5238. Min Act: -0.0000

Data Index: 452657 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.3662. Min Act: -0.0000

Data Index: 10960 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.3940. Min Act: -0.0000

Data Index: 435140 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.4734. Min Act: -0.0000

Data Index: 885420 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.3864. Min Act: -0.0000

Data Index: 43632 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.2800. Min Act: -0.0000

Data Index: 684224 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1329875 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.2823. Min Act: -0.0000

Data Index: 929897 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.3459. Min Act: -0.0000

Data Index: 867473 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.3189. Min Act: -0.0000

Data Index: 386617 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.3859. Min Act: -0.0000

Data Index: 636989 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.2902. Min Act: -0.0000

Data Index: 362758 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.2272. Min Act: -0.0000

Data Index: 26838 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.2363. Min Act: -0.0000

Data Index: 165026 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 2.2399. Min Range: -2.2399

Max Act: 1.2349. Min Act: -0.0000

Data Index: 711480 (C4 (Web Text))

Max Activating Token Index: 304