Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4647 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.5658. Min Act: -0.0000

Data Index: 969817 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4938. Min Act: -0.0000

Data Index: 782791 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.3457. Min Act: -0.0000

Data Index: 151350 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.3678. Min Act: -0.0000

Data Index: 591328 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.3708. Min Act: -0.0000

Data Index: 769992 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.3095. Min Act: -0.0000

Data Index: 968759 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.9534. Min Act: -0.0000

Data Index: 560613 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.8675. Min Act: -0.0000

Data Index: 741055 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.8923. Min Act: -0.0000

Data Index: 813423 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.9343. Min Act: -0.0000

Data Index: 581475 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1067133 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.8480. Min Act: -0.0000

Data Index: 112139 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1084649 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.8233. Min Act: -0.0000

Data Index: 488978 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.8205. Min Act: -0.0000

Data Index: 453616 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.8177. Min Act: -0.0000

Data Index: 896810 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1174124 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.8153. Min Act: -0.0000

Data Index: 61115 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.7536. Min Act: -0.0000

Data Index: 324597 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 1.5658. Min Range: -1.5658

Max Act: 0.7195. Min Act: -0.0000

Data Index: 754045 (C4 (Web Text))

Max Activating Token Index: 878