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

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

Neuron 1554 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8874. Min Act: -0.0001

Data Index: 255856 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8917. Min Act: -0.0001

Data Index: 1137433 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8291. Min Act: -0.0001

Data Index: 1261473 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7632. Min Act: -0.0001

Data Index: 948775 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7677. Min Act: -0.0001

Data Index: 470973 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7140. Min Act: -0.0001

Data Index: 65866 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7769. Min Act: -0.0001

Data Index: 887749 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7004. Min Act: -0.0001

Data Index: 653033 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7438. Min Act: -0.0001

Data Index: 177235 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6789. Min Act: -0.0001

Data Index: 1024331 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6990. Min Act: -0.0001

Data Index: 56479 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6511. Min Act: -0.0001

Data Index: 1046939 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6710. Min Act: -0.0001

Data Index: 220777 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6435. Min Act: -0.0001

Data Index: 1151287 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6455. Min Act: -0.0001

Data Index: 1236812 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7054. Min Act: -0.0001

Data Index: 312143 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6402. Min Act: -0.0001

Data Index: 943821 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6218. Min Act: -0.0001

Data Index: 629147 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6556. Min Act: -0.0001

Data Index: 924618 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6721. Min Act: -0.0001

Data Index: 136822 (C4 (Web Text))

Max Activating Token Index: 383