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

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

Neuron 3716 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: 2.1458. Min Range: -2.1458

Max Act: 2.1458. Min Act: -0.0000

Data Index: 281426 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 2.1458. Min Range: -2.1458

Max Act: 2.0104. Min Act: -0.0000

Data Index: 540748 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.8435. Min Act: -0.0000

Data Index: 643073 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.8778. Min Act: -0.0000

Data Index: 1352105 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.9496. Min Act: -0.0000

Data Index: 1073293 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6866. Min Act: -0.0000

Data Index: 534926 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.7620. Min Act: -0.0000

Data Index: 236 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.5804. Min Act: -0.0000

Data Index: 626244 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.8038. Min Act: -0.0000

Data Index: 893863 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.7123. Min Act: -0.0000

Data Index: 313628 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6531. Min Act: -0.0000

Data Index: 338184 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.7450. Min Act: -0.0000

Data Index: 34795 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.5836. Min Act: -0.0000

Data Index: 683857 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6701. Min Act: -0.0000

Data Index: 593303 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6238. Min Act: -0.0000

Data Index: 320032 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6205. Min Act: -0.0000

Data Index: 927435 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6675. Min Act: -0.0000

Data Index: 181331 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6658. Min Act: -0.0000

Data Index: 629629 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6425. Min Act: -0.0000

Data Index: 174568 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6487. Min Act: -0.0000

Data Index: 1128594 (C4 (Web Text))

Max Activating Token Index: 893