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

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

Neuron 794 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.1386. Min Act: -0.0001

Data Index: 332231 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9284. Min Act: -0.0001

Data Index: 635143 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.0824. Min Act: -0.0001

Data Index: 199371 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.0835. Min Act: -0.0001

Data Index: 695308 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.0217. Min Act: -0.0001

Data Index: 929683 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9942. Min Act: -0.0001

Data Index: 945451 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9788. Min Act: -0.0001

Data Index: 813119 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9668. Min Act: -0.0001

Data Index: 876400 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.0299. Min Act: -0.0001

Data Index: 673390 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9449. Min Act: -0.0001

Data Index: 588540 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9035. Min Act: -0.0001

Data Index: 81569 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8947. Min Act: -0.0001

Data Index: 544652 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8319. Min Act: -0.0001

Data Index: 1127382 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8448. Min Act: -0.0001

Data Index: 434879 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8998. Min Act: -0.0001

Data Index: 1334323 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8183. Min Act: -0.0001

Data Index: 855236 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9012. Min Act: -0.0001

Data Index: 553753 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8411. Min Act: -0.0001

Data Index: 618944 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8351. Min Act: -0.0001

Data Index: 864665 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8797. Min Act: -0.0001

Data Index: 482296 (C4 (Web Text))

Max Activating Token Index: 338