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

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

Neuron 849 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4409. Min Range: -5.4409

Max Act: 5.4409. Min Act: -0.0000

Data Index: 606367 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 5.4409. Min Range: -5.4409

Max Act: 5.3696. Min Act: -0.0000

Data Index: 239428 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 5.4409. Min Range: -5.4409

Max Act: 5.3035. Min Act: -0.0000

Data Index: 931505 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 5.4409. Min Range: -5.4409

Max Act: 5.3025. Min Act: -0.0000

Data Index: 818516 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 5.4409. Min Range: -5.4409

Max Act: 5.3973. Min Act: -0.0000

Data Index: 1017061 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 5.4409. Min Range: -5.4409

Max Act: 5.0478. Min Act: -0.0000

Data Index: 562616 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 5.4409. Min Range: -5.4409

Max Act: 5.1615. Min Act: -0.0000

Data Index: 387150 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.9249. Min Act: -0.0000

Data Index: 393492 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.8596. Min Act: -0.0000

Data Index: 854401 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.6366. Min Act: -0.0000

Data Index: 396844 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.6090. Min Act: -0.0000

Data Index: 1357247 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.7089. Min Act: -0.0000

Data Index: 1069101 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.6631. Min Act: -0.0000

Data Index: 487109 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.4366. Min Act: -0.0000

Data Index: 349567 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.4592. Min Act: -0.0000

Data Index: 713569 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.6279. Min Act: -0.0000

Data Index: 1353772 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.6168. Min Act: -0.0000

Data Index: 806509 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.5690. Min Act: -0.0000

Data Index: 832211 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.4370. Min Act: -0.0000

Data Index: 1335340 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 5.4409. Min Range: -5.4409

Max Act: 4.4483. Min Act: -0.0000

Data Index: 607857 (C4 (Web Text))

Max Activating Token Index: 881