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

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

Neuron 596 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8798. Min Act: -0.0001

Data Index: 353559 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8777. Min Act: -0.0001

Data Index: 390656 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8363. Min Act: -0.0001

Data Index: 1034317 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8321. Min Act: -0.0001

Data Index: 240975 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8479. Min Act: -0.0001

Data Index: 417076 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7949. Min Act: -0.0001

Data Index: 394490 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8260. Min Act: -0.0001

Data Index: 1033787 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8227. Min Act: -0.0001

Data Index: 317582 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7900. Min Act: -0.0001

Data Index: 974454 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7443. Min Act: -0.0001

Data Index: 84654 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7664. Min Act: -0.0001

Data Index: 1219267 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7174. Min Act: -0.0001

Data Index: 475634 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7602. Min Act: -0.0001

Data Index: 78297 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7572. Min Act: -0.0001

Data Index: 564821 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7698. Min Act: -0.0001

Data Index: 170462 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7701. Min Act: -0.0001

Data Index: 1189530 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7705. Min Act: -0.0001

Data Index: 222111 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7603. Min Act: -0.0001

Data Index: 1282291 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7115. Min Act: -0.0001

Data Index: 462828 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7574. Min Act: -0.0001

Data Index: 510865 (C4 (Web Text))

Max Activating Token Index: 27