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

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

Neuron 3041 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: 2.5683. Min Range: -2.5683

Max Act: 2.5683. Min Act: -0.0000

Data Index: 827356 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.3981. Min Act: -0.0000

Data Index: 1351880 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.3746. Min Act: -0.0000

Data Index: 513262 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.2765. Min Act: -0.0000

Data Index: 710046 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.0635. Min Act: -0.0000

Data Index: 659447 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.2108. Min Act: -0.0000

Data Index: 173788 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.2982. Min Act: -0.0000

Data Index: 353160 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.1743. Min Act: -0.0000

Data Index: 898752 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.1161. Min Act: -0.0000

Data Index: 1160105 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.2472. Min Act: -0.0000

Data Index: 160303 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.1140. Min Act: -0.0000

Data Index: 1149175 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.1508. Min Act: -0.0000

Data Index: 1305700 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 2.5683. Min Range: -2.5683

Max Act: 0.9917. Min Act: -0.0000

Data Index: 742669 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.0140. Min Act: -0.0000

Data Index: 947555 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 2.5683. Min Range: -2.5683

Max Act: 0.9827. Min Act: -0.0000

Data Index: 786167 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.0567. Min Act: -0.0000

Data Index: 346504 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.1447. Min Act: -0.0000

Data Index: 75705 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.0921. Min Act: -0.0000

Data Index: 116926 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.0309. Min Act: -0.0000

Data Index: 395132 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 2.5683. Min Range: -2.5683

Max Act: 0.9992. Min Act: -0.0000

Data Index: 181600 (C4 (Web Text))

Max Activating Token Index: 855