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

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

Neuron 3033 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0588. Min Act: -0.0001

Data Index: 649359 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0469. Min Act: -0.0001

Data Index: 668928 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0501. Min Act: -0.0001

Data Index: 451614 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0407. Min Act: -0.0001

Data Index: 918105 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0497. Min Act: -0.0001

Data Index: 1164961 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0485. Min Act: -0.0001

Data Index: 766329 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1022953 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0450. Min Act: -0.0001

Data Index: 729151 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0461. Min Act: -0.0001

Data Index: 905798 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0502. Min Act: -0.0001

Data Index: 945031 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0429. Min Act: -0.0001

Data Index: 385144 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1116981 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1090324 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1240571 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1341284 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0449. Min Act: -0.0001

Data Index: 557004 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1098604 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0433. Min Act: -0.0001

Data Index: 12747 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0401. Min Act: -0.0001

Data Index: 1293113 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0412. Min Act: -0.0001

Data Index: 735647 (C4 (Web Text))

Max Activating Token Index: 161