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

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

Neuron 2104 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.4195. Min Act: -0.0000

Data Index: 572437 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1046617 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2546. Min Act: -0.0000

Data Index: 676849 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2581. Min Act: -0.0000

Data Index: 991005 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2449. Min Act: -0.0000

Data Index: 726276 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2516. Min Act: -0.0000

Data Index: 341505 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2464. Min Act: -0.0000

Data Index: 425801 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2331. Min Act: -0.0000

Data Index: 727879 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1056325 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2351. Min Act: -0.0000

Data Index: 12427 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2247. Min Act: -0.0000

Data Index: 526880 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2161. Min Act: -0.0000

Data Index: 708524 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2072. Min Act: -0.0000

Data Index: 754192 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2122. Min Act: -0.0000

Data Index: 25080 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1116443 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1096575 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2057. Min Act: -0.0000

Data Index: 928128 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.1861. Min Act: -0.0000

Data Index: 340653 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.1973. Min Act: -0.0000

Data Index: 221423 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.1834. Min Act: 0.0000

Data Index: 1257495 (C4 (Web Text))

Max Activating Token Index: 283