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

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

Neuron 5347 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: 1.9438. Min Range: -1.9438

Max Act: 1.9438. Min Act: -0.0000

Data Index: 562731 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.7242. Min Act: -0.0000

Data Index: 1268771 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.7261. Min Act: -0.0000

Data Index: 1088365 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.6269. Min Act: -0.0000

Data Index: 905191 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.6572. Min Act: -0.0000

Data Index: 594720 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.5120. Min Act: -0.0000

Data Index: 952590 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.5825. Min Act: -0.0000

Data Index: 378520 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.6133. Min Act: -0.0000

Data Index: 562667 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.7978. Min Act: -0.0000

Data Index: 608314 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.5840. Min Act: -0.0000

Data Index: 647278 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.5326. Min Act: -0.0000

Data Index: 8437 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.4751. Min Act: -0.0000

Data Index: 310369 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.5603. Min Act: -0.0000

Data Index: 1083259 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.5087. Min Act: -0.0000

Data Index: 333574 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.5520. Min Act: -0.0000

Data Index: 1010312 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3748. Min Act: -0.0000

Data Index: 612238 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.4557. Min Act: -0.0000

Data Index: 944430 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.4505. Min Act: -0.0000

Data Index: 542645 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3930. Min Act: -0.0000

Data Index: 369512 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3842. Min Act: -0.0000

Data Index: 774552 (C4 (Web Text))

Max Activating Token Index: 42