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

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

Neuron 4976 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6749. Min Range: -7.6749

Max Act: 7.6749. Min Act: -0.0000

Data Index: 1554357 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 7.6749. Min Range: -7.6749

Max Act: 6.8799. Min Act: -0.0000

Data Index: 308205 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 7.6749. Min Range: -7.6749

Max Act: 6.8503. Min Act: -0.0000

Data Index: 1566915 (Python Code)

Max Activating Token Index: 259

Text #3

Max Range: 7.6749. Min Range: -7.6749

Max Act: 6.9913. Min Act: -0.0000

Data Index: 1419432 (Python Code)

Max Activating Token Index: 995

Text #4

Max Range: 7.6749. Min Range: -7.6749

Max Act: 6.6889. Min Act: -0.0000

Data Index: 20561 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 7.6749. Min Range: -7.6749

Max Act: 6.4792. Min Act: -0.0000

Data Index: 897191 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 7.6749. Min Range: -7.6749

Max Act: 6.1064. Min Act: -0.0000

Data Index: 1650298 (Python Code)

Max Activating Token Index: 259

Text #7

Max Range: 7.6749. Min Range: -7.6749

Max Act: 5.8072. Min Act: -0.0000

Data Index: 630821 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 7.6749. Min Range: -7.6749

Max Act: 5.9223. Min Act: -0.0000

Data Index: 1374838 (Python Code)

Max Activating Token Index: 318

Text #9

Max Range: 7.6749. Min Range: -7.6749

Max Act: 5.9473. Min Act: -0.0000

Data Index: 992167 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 7.6749. Min Range: -7.6749

Max Act: 5.7493. Min Act: -0.0000

Data Index: 195374 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 7.6749. Min Range: -7.6749

Max Act: 6.0504. Min Act: -0.0000

Data Index: 1151677 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 7.6749. Min Range: -7.6749

Max Act: 5.9911. Min Act: -0.0000

Data Index: 1347968 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 7.6749. Min Range: -7.6749

Max Act: 6.0685. Min Act: -0.0000

Data Index: 1183159 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 7.6749. Min Range: -7.6749

Max Act: 5.5994. Min Act: -0.0000

Data Index: 785920 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 7.6749. Min Range: -7.6749

Max Act: 5.3270. Min Act: -0.0000

Data Index: 699307 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 7.6749. Min Range: -7.6749

Max Act: 5.6734. Min Act: -0.0000

Data Index: 450897 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 7.6749. Min Range: -7.6749

Max Act: 5.8456. Min Act: -0.0000

Data Index: 1653274 (Python Code)

Max Activating Token Index: 1007

Text #18

Max Range: 7.6749. Min Range: -7.6749

Max Act: 5.5563. Min Act: -0.0000

Data Index: 1453868 (Python Code)

Max Activating Token Index: 507

Text #19

Max Range: 7.6749. Min Range: -7.6749

Max Act: 5.3321. Min Act: -0.0000

Data Index: 1096236 (C4 (Web Text))

Max Activating Token Index: 382