Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2383 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.3123. Min Range: -2.3123

Max Act: 2.3123. Min Act: -0.0000

Data Index: 961444 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 2.3123. Min Range: -2.3123

Max Act: 2.1533. Min Act: -0.0001

Data Index: 652527 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.9923. Min Act: -0.0000

Data Index: 980192 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.8068. Min Act: -0.0000

Data Index: 497846 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.8466. Min Act: -0.0000

Data Index: 1231348 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.8096. Min Act: -0.0000

Data Index: 708149 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6605. Min Act: -0.0000

Data Index: 802474 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6434. Min Act: -0.0000

Data Index: 401474 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6755. Min Act: -0.0000

Data Index: 565995 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6869. Min Act: -0.0000

Data Index: 935453 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6092. Min Act: -0.0000

Data Index: 262498 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.5459. Min Act: -0.0000

Data Index: 90132 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6396. Min Act: -0.0000

Data Index: 811911 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6136. Min Act: -0.0000

Data Index: 113345 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6445. Min Act: -0.0001

Data Index: 640969 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6966. Min Act: -0.0000

Data Index: 357177 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6428. Min Act: -0.0000

Data Index: 923739 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6633. Min Act: -0.0000

Data Index: 1159582 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.6135. Min Act: -0.0000

Data Index: 631469 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 2.3123. Min Range: -2.3123

Max Act: 1.5901. Min Act: -0.0000

Data Index: 89344 (C4 (Web Text))

Max Activating Token Index: 594