Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 892 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0964. Min Act: -0.0001

Data Index: 459914 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0834. Min Act: -0.0001

Data Index: 1049756 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0836. Min Act: -0.0001

Data Index: 420019 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0807. Min Act: -0.0001

Data Index: 638449 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0806. Min Act: -0.0000

Data Index: 41831 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0830. Min Act: -0.0000

Data Index: 862896 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1057739 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0741. Min Act: -0.0001

Data Index: 206655 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0764. Min Act: -0.0001

Data Index: 683853 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0708. Min Act: -0.0001

Data Index: 544005 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1296734 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1256575 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0689. Min Act: -0.0001

Data Index: 560581 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0718. Min Act: -0.0001

Data Index: 412320 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1024369 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0719. Min Act: -0.0001

Data Index: 138520 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1111170 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1101393 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0699. Min Act: -0.0001

Data Index: 267212 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0700. Min Act: -0.0000

Data Index: 303328 (C4 (Web Text))

Max Activating Token Index: 750