Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3658 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0723. Min Range: -1.0723

Max Act: 1.0723. Min Act: -0.0000

Data Index: 324888 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 1.0723. Min Range: -1.0723

Max Act: 1.0324. Min Act: -0.0000

Data Index: 705381 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 1.0723. Min Range: -1.0723

Max Act: 1.0676. Min Act: -0.0000

Data Index: 199092 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.0723. Min Range: -1.0723

Max Act: 1.0265. Min Act: -0.0000

Data Index: 1140383 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.9642. Min Act: -0.0000

Data Index: 723414 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 1.0723. Min Range: -1.0723

Max Act: 1.0318. Min Act: -0.0000

Data Index: 122967 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.9808. Min Act: -0.0000

Data Index: 802040 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1084550 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.9563. Min Act: 0.0000

Data Index: 1080280 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8850. Min Act: -0.0000

Data Index: 499264 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1164943 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.9471. Min Act: -0.0000

Data Index: 645916 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8245. Min Act: -0.0000

Data Index: 791173 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8785. Min Act: -0.0000

Data Index: 353612 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8722. Min Act: 0.0001

Data Index: 326620 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.9011. Min Act: -0.0000

Data Index: 43224 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8515. Min Act: -0.0000

Data Index: 887300 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7942. Min Act: -0.0000

Data Index: 129761 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8300. Min Act: -0.0000

Data Index: 811447 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1271633 (C4 (Web Text))

Max Activating Token Index: 749