Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1806 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1176. Min Act: -0.0001

Data Index: 448345 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1138. Min Act: -0.0001

Data Index: 64998 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1600498 (Python Code)

Max Activating Token Index: 523

Text #3

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1089. Min Act: -0.0001

Data Index: 864651 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1625004 (Python Code)

Max Activating Token Index: 193

Text #5

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1003. Min Act: -0.0001

Data Index: 691363 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0959. Min Act: -0.0001

Data Index: 328618 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0942. Min Act: -0.0001

Data Index: 5988 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0905. Min Act: -0.0001

Data Index: 521080 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1194844 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0899. Min Act: -0.0001

Data Index: 868383 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0890. Min Act: -0.0001

Data Index: 435769 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1357104 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1171198 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0808. Min Act: -0.0001

Data Index: 462643 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0875. Min Act: -0.0001

Data Index: 6922 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1484180 (Python Code)

Max Activating Token Index: 121

Text #17

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0908. Min Act: -0.0001

Data Index: 650576 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0912. Min Act: -0.0001

Data Index: 482291 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0892. Min Act: -0.0001

Data Index: 231044 (C4 (Web Text))

Max Activating Token Index: 458