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

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

Neuron 2000 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0466. Min Range: -1.0466

Max Act: 1.0466. Min Act: -0.0001

Data Index: 824383 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 1.0466. Min Range: -1.0466

Max Act: 1.0367. Min Act: -0.0001

Data Index: 235581 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8529. Min Act: -0.0001

Data Index: 343993 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1167009 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8375. Min Act: -0.0000

Data Index: 978820 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7857. Min Act: -0.0001

Data Index: 1089449 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1057615 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8285. Min Act: -0.0000

Data Index: 913106 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8021. Min Act: -0.0001

Data Index: 144526 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8196. Min Act: -0.0000

Data Index: 100901 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7749. Min Act: -0.0000

Data Index: 858338 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8164. Min Act: -0.0000

Data Index: 687048 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7544. Min Act: -0.0000

Data Index: 615494 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7529. Min Act: -0.0001

Data Index: 449721 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7020. Min Act: -0.0001

Data Index: 110124 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7399. Min Act: -0.0000

Data Index: 82537 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7031. Min Act: -0.0000

Data Index: 355389 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7234. Min Act: -0.0001

Data Index: 265691 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7125. Min Act: -0.0000

Data Index: 564763 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7388. Min Act: -0.0000

Data Index: 597169 (C4 (Web Text))

Max Activating Token Index: 473