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

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

Neuron 265 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3676. Min Act: -0.0005

Data Index: 373873 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3854. Min Act: -0.0005

Data Index: 612740 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3964. Min Act: -0.0005

Data Index: 240558 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3870. Min Act: -0.0005

Data Index: 931286 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3421. Min Act: -0.0005

Data Index: 544220 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3590. Min Act: -0.0005

Data Index: 288794 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3566. Min Act: -0.0005

Data Index: 108361 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3566. Min Act: -0.0005

Data Index: 1240079 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3517. Min Act: -0.0005

Data Index: 34095 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3410. Min Act: -0.0005

Data Index: 1112323 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3504. Min Act: -0.0005

Data Index: 349693 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3223. Min Act: -0.0005

Data Index: 1126970 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3258. Min Act: -0.0005

Data Index: 864965 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3347. Min Act: -0.0005

Data Index: 569254 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3217. Min Act: -0.0005

Data Index: 880988 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3354. Min Act: -0.0005

Data Index: 981192 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3367. Min Act: -0.0005

Data Index: 83138 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3343. Min Act: -0.0005

Data Index: 180245 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3235. Min Act: -0.0005

Data Index: 771349 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2925. Min Act: -0.0005

Data Index: 1234524 (C4 (Web Text))

Max Activating Token Index: 973