Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3552 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1792. Min Range: -1.1792

Max Act: 1.1792. Min Act: -0.0001

Data Index: 898486 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 1.1792. Min Range: -1.1792

Max Act: 1.0307. Min Act: -0.0001

Data Index: 1067424 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 1.1792. Min Range: -1.1792

Max Act: 1.0062. Min Act: -0.0001

Data Index: 846664 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.9696. Min Act: -0.0001

Data Index: 449583 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.9635. Min Act: -0.0001

Data Index: 795534 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 1.1792. Min Range: -1.1792

Max Act: 1.0170. Min Act: -0.0001

Data Index: 227006 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.8776. Min Act: -0.0001

Data Index: 863823 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.9651. Min Act: -0.0001

Data Index: 95686 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.9652. Min Act: -0.0001

Data Index: 808631 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.8869. Min Act: -0.0001

Data Index: 610865 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.9281. Min Act: -0.0001

Data Index: 728434 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.8913. Min Act: -0.0001

Data Index: 805535 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.8617. Min Act: -0.0001

Data Index: 1529846 (Python Code)

Max Activating Token Index: 669

Text #13

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.8711. Min Act: -0.0001

Data Index: 770299 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.8395. Min Act: -0.0001

Data Index: 1015344 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.8874. Min Act: -0.0001

Data Index: 326222 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.8879. Min Act: -0.0001

Data Index: 209028 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.8289. Min Act: -0.0001

Data Index: 1307479 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.8208. Min Act: -0.0001

Data Index: 1021625 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.8678. Min Act: -0.0001

Data Index: 315152 (C4 (Web Text))

Max Activating Token Index: 350