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

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

Neuron 3410 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.8708. Min Act: -0.0000

Data Index: 557360 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.8966. Min Act: -0.0000

Data Index: 545531 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1193935 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1073658 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.9369. Min Act: -0.0000

Data Index: 557269 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.8360. Min Act: -0.0000

Data Index: 770536 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7864. Min Act: -0.0000

Data Index: 309541 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.8248. Min Act: -0.0000

Data Index: 620431 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.8268. Min Act: -0.0000

Data Index: 638422 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1203909 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7960. Min Act: -0.0000

Data Index: 129238 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7775. Min Act: -0.0000

Data Index: 270580 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7746. Min Act: -0.0000

Data Index: 413195 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1352610 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7146. Min Act: -0.0000

Data Index: 637404 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7584. Min Act: -0.0000

Data Index: 89446 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7264. Min Act: -0.0000

Data Index: 241947 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6875. Min Act: -0.0000

Data Index: 826563 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6908. Min Act: -0.0000

Data Index: 426313 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6501. Min Act: -0.0000

Data Index: 927128 (C4 (Web Text))

Max Activating Token Index: 195