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

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

Neuron 1903 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0536. Min Range: -2.0536

Max Act: 2.0536. Min Act: -0.0000

Data Index: 1273340 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.6907. Min Act: -0.0000

Data Index: 57929 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.6766. Min Act: -0.0000

Data Index: 467954 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.6588. Min Act: -0.0000

Data Index: 284671 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.6086. Min Act: -0.0000

Data Index: 1242402 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.6052. Min Act: -0.0000

Data Index: 1217854 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.5990. Min Act: -0.0000

Data Index: 1085830 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.6755. Min Act: -0.0000

Data Index: 681698 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.4845. Min Act: -0.0000

Data Index: 141303 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.5328. Min Act: -0.0000

Data Index: 596599 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.5118. Min Act: -0.0000

Data Index: 612831 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.5044. Min Act: -0.0000

Data Index: 1076920 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.5112. Min Act: -0.0000

Data Index: 366122 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.4071. Min Act: -0.0000

Data Index: 66357 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.3662. Min Act: -0.0000

Data Index: 1157354 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.3746. Min Act: -0.0000

Data Index: 60954 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.3801. Min Act: -0.0000

Data Index: 1152590 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.4619. Min Act: -0.0000

Data Index: 387197 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.3721. Min Act: -0.0000

Data Index: 214356 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 2.0536. Min Range: -2.0536

Max Act: 1.4293. Min Act: -0.0000

Data Index: 596024 (C4 (Web Text))

Max Activating Token Index: 262