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

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

Neuron 1544 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4634. Min Act: -0.0001

Data Index: 386488 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4634. Min Act: -0.0001

Data Index: 681686 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4555. Min Act: -0.0001

Data Index: 930690 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4470. Min Act: -0.0001

Data Index: 228475 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4329. Min Act: -0.0001

Data Index: 738586 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.3985. Min Act: -0.0001

Data Index: 315981 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.3931. Min Act: -0.0001

Data Index: 1317245 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4153. Min Act: -0.0001

Data Index: 1173759 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.3922. Min Act: -0.0001

Data Index: 121703 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4196. Min Act: -0.0001

Data Index: 950744 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.3718. Min Act: -0.0001

Data Index: 767129 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.3877. Min Act: -0.0001

Data Index: 4343 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4128. Min Act: -0.0001

Data Index: 846995 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4079. Min Act: -0.0001

Data Index: 304201 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.3834. Min Act: -0.0001

Data Index: 1345290 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4111. Min Act: -0.0001

Data Index: 720291 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4240. Min Act: -0.0001

Data Index: 1022183 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4094. Min Act: -0.0001

Data Index: 1165415 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.3888. Min Act: -0.0001

Data Index: 366435 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.3705. Min Act: -0.0001

Data Index: 819000 (C4 (Web Text))

Max Activating Token Index: 363