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

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

Neuron 4062 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3572. Min Act: -0.0001

Data Index: 873941 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3260. Min Act: -0.0001

Data Index: 568636 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3052. Min Act: -0.0001

Data Index: 1332828 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3298. Min Act: -0.0001

Data Index: 770812 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2968. Min Act: -0.0001

Data Index: 311397 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3215. Min Act: -0.0001

Data Index: 927852 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2935. Min Act: -0.0001

Data Index: 287835 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3224. Min Act: -0.0001

Data Index: 913656 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2950. Min Act: -0.0001

Data Index: 15853 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2924. Min Act: -0.0001

Data Index: 237504 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3003. Min Act: -0.0001

Data Index: 1128167 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3232. Min Act: -0.0001

Data Index: 309801 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3117. Min Act: -0.0001

Data Index: 493252 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3072. Min Act: -0.0001

Data Index: 197486 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2960. Min Act: -0.0001

Data Index: 959 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2880. Min Act: -0.0001

Data Index: 644278 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3006. Min Act: -0.0001

Data Index: 15201 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3155. Min Act: -0.0001

Data Index: 956691 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3065. Min Act: -0.0001

Data Index: 1804 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2968. Min Act: -0.0001

Data Index: 1258000 (C4 (Web Text))

Max Activating Token Index: 728