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

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

Neuron 581 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3410. Min Range: -2.3410

Max Act: 2.3410. Min Act: -0.0000

Data Index: 59170 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.7610. Min Act: -0.0000

Data Index: 786168 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.6742. Min Act: -0.0000

Data Index: 1350651 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.7394. Min Act: -0.0000

Data Index: 1341834 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.5846. Min Act: -0.0000

Data Index: 736996 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.7292. Min Act: -0.0000

Data Index: 442417 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.6400. Min Act: -0.0000

Data Index: 98708 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1047843 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.7061. Min Act: -0.0000

Data Index: 392523 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.4688. Min Act: -0.0000

Data Index: 1612492 (Python Code)

Max Activating Token Index: 736

Text #10

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.5132. Min Act: -0.0000

Data Index: 880952 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.4948. Min Act: 0.0000

Data Index: 22154 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.4847. Min Act: -0.0000

Data Index: 502465 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.5329. Min Act: -0.0000

Data Index: 396234 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.5166. Min Act: -0.0000

Data Index: 1082821 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.4078. Min Act: -0.0000

Data Index: 1303397 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.4709. Min Act: -0.0000

Data Index: 261497 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.4805. Min Act: -0.0000

Data Index: 47007 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.3861. Min Act: -0.0000

Data Index: 1279047 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 2.3410. Min Range: -2.3410

Max Act: 1.2961. Min Act: -0.0000

Data Index: 2614 (C4 (Web Text))

Max Activating Token Index: 220