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

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

Neuron 4589 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.8068. Min Act: -0.0000

Data Index: 410234 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.7774. Min Act: -0.0000

Data Index: 564258 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6440. Min Act: -0.0000

Data Index: 908514 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6554. Min Act: -0.0000

Data Index: 862358 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.5729. Min Act: -0.0000

Data Index: 909618 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1283920 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1308997 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6087. Min Act: -0.0000

Data Index: 864761 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.5303. Min Act: -0.0000

Data Index: 400558 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.4869. Min Act: -0.0000

Data Index: 617943 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1237833 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1327688 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.5630. Min Act: -0.0000

Data Index: 1069908 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.5102. Min Act: -0.0000

Data Index: 559456 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.5425. Min Act: -0.0000

Data Index: 273369 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.5031. Min Act: -0.0000

Data Index: 866978 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.5319. Min Act: -0.0000

Data Index: 500896 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1083946 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.4836. Min Act: -0.0000

Data Index: 758241 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1133665 (C4 (Web Text))

Max Activating Token Index: 155