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

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

Neuron 1943 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: 4.7092. Min Range: -4.7092

Max Act: 4.7092. Min Act: -0.0000

Data Index: 402200 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 4.7092. Min Range: -4.7092

Max Act: 4.6772. Min Act: -0.0000

Data Index: 1161487 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 4.7092. Min Range: -4.7092

Max Act: 4.5186. Min Act: -0.0000

Data Index: 618184 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 4.7092. Min Range: -4.7092

Max Act: 4.3254. Min Act: -0.0000

Data Index: 181758 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 4.7092. Min Range: -4.7092

Max Act: 4.3963. Min Act: -0.0000

Data Index: 662222 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 4.7092. Min Range: -4.7092

Max Act: 4.4768. Min Act: -0.0000

Data Index: 1266657 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 4.7092. Min Range: -4.7092

Max Act: 4.3415. Min Act: -0.0000

Data Index: 705696 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 4.7092. Min Range: -4.7092

Max Act: 4.2510. Min Act: -0.0000

Data Index: 1059029 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 4.7092. Min Range: -4.7092

Max Act: 4.0212. Min Act: -0.0000

Data Index: 235192 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 4.7092. Min Range: -4.7092

Max Act: 4.0546. Min Act: -0.0000

Data Index: 1333747 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 4.7092. Min Range: -4.7092

Max Act: 3.6280. Min Act: -0.0000

Data Index: 59430 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 4.7092. Min Range: -4.7092

Max Act: 3.6518. Min Act: -0.0000

Data Index: 132192 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 4.7092. Min Range: -4.7092

Max Act: 3.5453. Min Act: -0.0000

Data Index: 617407 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 4.7092. Min Range: -4.7092

Max Act: 3.4255. Min Act: -0.0000

Data Index: 676171 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 4.7092. Min Range: -4.7092

Max Act: 3.4908. Min Act: -0.0000

Data Index: 1169439 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 4.7092. Min Range: -4.7092

Max Act: 3.6054. Min Act: -0.0000

Data Index: 826211 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 4.7092. Min Range: -4.7092

Max Act: 3.3744. Min Act: -0.0000

Data Index: 867032 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 4.7092. Min Range: -4.7092

Max Act: 3.1823. Min Act: -0.0000

Data Index: 659728 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 4.7092. Min Range: -4.7092

Max Act: 3.2212. Min Act: -0.0000

Data Index: 311969 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 4.7092. Min Range: -4.7092

Max Act: 3.3225. Min Act: -0.0000

Data Index: 34005 (C4 (Web Text))

Max Activating Token Index: 268