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

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

Neuron 1685 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0773. Min Range: -1.0773

Max Act: 1.0273. Min Act: -0.0000

Data Index: 1523183 (Python Code)

Max Activating Token Index: 625

Text #1

Max Range: 1.0773. Min Range: -1.0773

Max Act: 1.0773. Min Act: -0.0000

Data Index: 1295829 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9017. Min Act: -0.0000

Data Index: 157486 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9113. Min Act: -0.0000

Data Index: 883354 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9307. Min Act: -0.0000

Data Index: 333219 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1435215 (Python Code)

Max Activating Token Index: 871

Text #6

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8030. Min Act: -0.0000

Data Index: 526737 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1253821 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1201225 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7922. Min Act: -0.0000

Data Index: 545858 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7812. Min Act: -0.0000

Data Index: 886147 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8280. Min Act: -0.0000

Data Index: 615396 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7723. Min Act: -0.0000

Data Index: 961671 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1147035 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8239. Min Act: -0.0000

Data Index: 541233 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7652. Min Act: -0.0000

Data Index: 601367 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1611999 (Python Code)

Max Activating Token Index: 281

Text #17

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7503. Min Act: -0.0000

Data Index: 166972 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7265. Min Act: -0.0000

Data Index: 330875 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7507. Min Act: -0.0000

Data Index: 429637 (C4 (Web Text))

Max Activating Token Index: 384