Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2837 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6732. Min Act: -0.0000

Data Index: 415449 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6274. Min Act: -0.0000

Data Index: 401837 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6318. Min Act: -0.0000

Data Index: 694016 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1237113 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5702. Min Act: -0.0000

Data Index: 679611 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5848. Min Act: -0.0000

Data Index: 257356 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1213733 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5942. Min Act: -0.0000

Data Index: 608228 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1305118 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5330. Min Act: -0.0000

Data Index: 616707 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1020540 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5539. Min Act: -0.0000

Data Index: 822721 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5486. Min Act: -0.0000

Data Index: 993083 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5236. Min Act: -0.0000

Data Index: 914832 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4894. Min Act: -0.0000

Data Index: 796540 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5574. Min Act: -0.0000

Data Index: 382839 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5721. Min Act: -0.0000

Data Index: 893028 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1095826 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1150178 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1240393 (C4 (Web Text))

Max Activating Token Index: 44