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

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

Neuron 3066 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: 1.5175. Min Range: -1.5175

Max Act: 1.4842. Min Act: -0.0000

Data Index: 1086542 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.5175. Min Act: -0.0000

Data Index: 1282888 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.3015. Min Act: -0.0000

Data Index: 19364 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.4060. Min Act: -0.0000

Data Index: 815930 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.3763. Min Act: -0.0000

Data Index: 115089 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.3710. Min Act: -0.0000

Data Index: 1298853 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.1579. Min Act: -0.0000

Data Index: 374165 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1213997 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1298988 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1326618 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.1368. Min Act: -0.0000

Data Index: 622604 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.1548. Min Act: -0.0000

Data Index: 897056 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.0984. Min Act: -0.0000

Data Index: 82259 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.0644. Min Act: -0.0000

Data Index: 1280392 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.1156. Min Act: -0.0000

Data Index: 852486 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.0414. Min Act: -0.0000

Data Index: 81302 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1022748 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.9662. Min Act: -0.0000

Data Index: 659007 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.9765. Min Act: -0.0000

Data Index: 182938 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1074209 (C4 (Web Text))

Max Activating Token Index: 798