Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4749 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1058834 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1152930 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4255. Min Act: -0.0000

Data Index: 135960 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3852. Min Act: -0.0000

Data Index: 928305 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1192141 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3436. Min Act: -0.0000

Data Index: 753757 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1314392 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3243. Min Act: -0.0000

Data Index: 664706 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3261. Min Act: -0.0000

Data Index: 342576 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3105. Min Act: -0.0000

Data Index: 443360 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2938. Min Act: -0.0000

Data Index: 255397 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3153. Min Act: -0.0000

Data Index: 465132 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2900. Min Act: -0.0000

Data Index: 574309 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3086. Min Act: -0.0000

Data Index: 408990 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3045. Min Act: -0.0000

Data Index: 489122 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2920. Min Act: -0.0000

Data Index: 413903 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2560. Min Act: -0.0000

Data Index: 660960 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2755. Min Act: -0.0000

Data Index: 795228 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1316367 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1203119 (C4 (Web Text))

Max Activating Token Index: 325