Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2708 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0949. Min Range: -4.0949

Max Act: 4.0949. Min Act: -0.0000

Data Index: 728217 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.6858. Min Act: -0.0000

Data Index: 831473 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.5740. Min Act: -0.0000

Data Index: 1079665 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.8718. Min Act: -0.0000

Data Index: 350251 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.6846. Min Act: -0.0000

Data Index: 1099250 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.6711. Min Act: -0.0001

Data Index: 456350 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.5605. Min Act: -0.0000

Data Index: 781320 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.5470. Min Act: -0.0000

Data Index: 110049 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.3257. Min Act: -0.0000

Data Index: 1092087 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.3256. Min Act: -0.0001

Data Index: 1275922 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.5925. Min Act: -0.0000

Data Index: 520928 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.1427. Min Act: -0.0000

Data Index: 485833 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 4.0949. Min Range: -4.0949

Max Act: 2.9588. Min Act: -0.0000

Data Index: 952500 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.4212. Min Act: -0.0000

Data Index: 713082 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.2170. Min Act: -0.0000

Data Index: 641062 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.3457. Min Act: -0.0000

Data Index: 1241782 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.1822. Min Act: -0.0000

Data Index: 41524 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 4.0949. Min Range: -4.0949

Max Act: 2.9184. Min Act: -0.0000

Data Index: 1346631 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.2055. Min Act: -0.0001

Data Index: 1640161 (Python Code)

Max Activating Token Index: 735

Text #19

Max Range: 4.0949. Min Range: -4.0949

Max Act: 3.3259. Min Act: -0.0001

Data Index: 451213 (C4 (Web Text))

Max Activating Token Index: 872