Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5581 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0200. Min Range: -2.0200

Max Act: 2.0200. Min Act: -0.0000

Data Index: 746942 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.5669. Min Act: -0.0000

Data Index: 66217 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1124672 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.5572. Min Act: -0.0000

Data Index: 900722 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.5483. Min Act: -0.0000

Data Index: 1222279 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.4706. Min Act: -0.0000

Data Index: 471381 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.4928. Min Act: -0.0000

Data Index: 1157973 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.3013. Min Act: -0.0000

Data Index: 906491 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1310180 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1277726 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.3337. Min Act: -0.0000

Data Index: 150487 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.3560. Min Act: -0.0000

Data Index: 255997 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.2727. Min Act: -0.0000

Data Index: 1274157 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.2108. Min Act: -0.0000

Data Index: 58661 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1029653 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.1845. Min Act: -0.0000

Data Index: 678119 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.1194. Min Act: -0.0000

Data Index: 730900 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.0313. Min Act: -0.0000

Data Index: 223364 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.0688. Min Act: -0.0000

Data Index: 532705 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 2.0200. Min Range: -2.0200

Max Act: 1.0575. Min Act: -0.0000

Data Index: 1256114 (C4 (Web Text))

Max Activating Token Index: 168