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

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

Neuron 5526 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: 1.1427. Min Range: -1.1427

Max Act: 1.1427. Min Act: -0.0001

Data Index: 1115651 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.1427. Min Range: -1.1427

Max Act: 1.0650. Min Act: -0.0001

Data Index: 147891 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 1.1427. Min Range: -1.1427

Max Act: 1.0029. Min Act: -0.0001

Data Index: 1246042 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.9063. Min Act: -0.0001

Data Index: 566857 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.9260. Min Act: -0.0001

Data Index: 619021 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8913. Min Act: -0.0001

Data Index: 284431 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8797. Min Act: -0.0001

Data Index: 1035081 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8847. Min Act: -0.0001

Data Index: 356516 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8919. Min Act: -0.0001

Data Index: 810491 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8623. Min Act: -0.0001

Data Index: 969614 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8561. Min Act: -0.0001

Data Index: 1186481 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8189. Min Act: -0.0001

Data Index: 213355 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8373. Min Act: -0.0001

Data Index: 420494 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8098. Min Act: -0.0001

Data Index: 705340 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.7176. Min Act: -0.0001

Data Index: 926925 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8577. Min Act: -0.0001

Data Index: 818027 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8226. Min Act: -0.0001

Data Index: 988935 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8693. Min Act: -0.0001

Data Index: 1163810 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.7969. Min Act: -0.0001

Data Index: 1043179 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8103. Min Act: -0.0001

Data Index: 899127 (C4 (Web Text))

Max Activating Token Index: 630