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

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

Neuron 3299 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.3884. Min Act: 0.0002

Data Index: 886361 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1067770 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.3507. Min Act: 0.0002

Data Index: 974662 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2980. Min Act: -0.0001

Data Index: 294997 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.3044. Min Act: 0.0003

Data Index: 268516 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.3001. Min Act: 0.0003

Data Index: 536040 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2874. Min Act: -0.0001

Data Index: 402887 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1169891 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2887. Min Act: -0.0000

Data Index: 441618 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2848. Min Act: -0.0001

Data Index: 507950 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2786. Min Act: 0.0000

Data Index: 874309 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2752. Min Act: -0.0000

Data Index: 480040 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2796. Min Act: -0.0000

Data Index: 42913 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2714. Min Act: 0.0000

Data Index: 995906 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2810. Min Act: 0.0003

Data Index: 380297 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1230630 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1119217 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2503. Min Act: 0.0002

Data Index: 403887 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2588. Min Act: -0.0000

Data Index: 90519 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.3884. Min Range: -0.3884

Max Act: 0.2463. Min Act: 0.0001

Data Index: 875528 (C4 (Web Text))

Max Activating Token Index: 760