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

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

Neuron 3671 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: 0.7760. Min Range: -0.7760

Max Act: 0.7699. Min Act: -0.0000

Data Index: 711430 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1267724 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.6989. Min Act: -0.0000

Data Index: 237307 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1309175 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.6465. Min Act: -0.0000

Data Index: 805178 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5735. Min Act: -0.0000

Data Index: 442138 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.6010. Min Act: -0.0000

Data Index: 428915 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5759. Min Act: -0.0000

Data Index: 440204 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1355496 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5667. Min Act: -0.0000

Data Index: 158130 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1227376 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5678. Min Act: -0.0000

Data Index: 332021 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5606. Min Act: -0.0000

Data Index: 395438 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1031117 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5612. Min Act: -0.0000

Data Index: 796066 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1381288 (Python Code)

Max Activating Token Index: 955

Text #16

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.6010. Min Act: -0.0000

Data Index: 354470 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1367203 (Python Code)

Max Activating Token Index: 989

Text #18

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1260811 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.7760. Min Range: -0.7760

Max Act: 0.5321. Min Act: -0.0000

Data Index: 507245 (C4 (Web Text))

Max Activating Token Index: 684