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

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

Neuron 3120 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1075520 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1352724 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6546. Min Act: -0.0000

Data Index: 178074 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6467. Min Act: -0.0000

Data Index: 253120 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6226. Min Act: -0.0000

Data Index: 664307 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1269832 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6317. Min Act: -0.0000

Data Index: 290068 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6469. Min Act: -0.0000

Data Index: 293154 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6327. Min Act: -0.0000

Data Index: 494935 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6214. Min Act: -0.0000

Data Index: 650591 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.5887. Min Act: -0.0000

Data Index: 272870 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6241. Min Act: -0.0000

Data Index: 877058 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6094. Min Act: -0.0000

Data Index: 660077 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6103. Min Act: -0.0000

Data Index: 617173 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1033251 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.5772. Min Act: -0.0000

Data Index: 550202 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1034687 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.5991. Min Act: -0.0000

Data Index: 638094 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6139. Min Act: -0.0000

Data Index: 274102 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.5614. Min Act: -0.0000

Data Index: 118886 (C4 (Web Text))

Max Activating Token Index: 916