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

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

Neuron 59 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: 4.3076. Min Range: -4.3076

Max Act: 4.3076. Min Act: -0.0000

Data Index: 176215 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 4.3076. Min Range: -4.3076

Max Act: 3.7152. Min Act: -0.0000

Data Index: 1068873 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.8268. Min Act: -0.0000

Data Index: 1499715 (Python Code)

Max Activating Token Index: 990

Text #3

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.6877. Min Act: -0.0000

Data Index: 641335 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.4576. Min Act: -0.0000

Data Index: 1585370 (Python Code)

Max Activating Token Index: 776

Text #5

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.3176. Min Act: -0.0000

Data Index: 1426146 (Python Code)

Max Activating Token Index: 906

Text #6

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.3449. Min Act: -0.0000

Data Index: 622534 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.4821. Min Act: -0.0000

Data Index: 1606261 (Python Code)

Max Activating Token Index: 463

Text #8

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.4672. Min Act: -0.0000

Data Index: 230322 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.2970. Min Act: -0.0000

Data Index: 511081 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.3698. Min Act: -0.0000

Data Index: 1509810 (Python Code)

Max Activating Token Index: 649

Text #11

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.1884. Min Act: -0.0000

Data Index: 1590984 (Python Code)

Max Activating Token Index: 735

Text #12

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.1322. Min Act: -0.0000

Data Index: 166129 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.3287. Min Act: -0.0000

Data Index: 555233 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.2032. Min Act: -0.0000

Data Index: 1090261 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.2156. Min Act: -0.0000

Data Index: 1625622 (Python Code)

Max Activating Token Index: 965

Text #16

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.1861. Min Act: -0.0000

Data Index: 60067 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.2743. Min Act: -0.0000

Data Index: 656723 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.0383. Min Act: -0.0000

Data Index: 425720 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 4.3076. Min Range: -4.3076

Max Act: 2.1543. Min Act: -0.0000

Data Index: 1531252 (Python Code)

Max Activating Token Index: 88