Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1680 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2235. Min Act: -0.0001

Data Index: 1355500 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2051. Min Act: -0.0001

Data Index: 254531 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1942. Min Act: -0.0001

Data Index: 666364 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1938. Min Act: -0.0001

Data Index: 672395 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1843. Min Act: -0.0001

Data Index: 47139 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2007. Min Act: -0.0001

Data Index: 494390 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1887. Min Act: -0.0001

Data Index: 472432 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1007171 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1686. Min Act: -0.0001

Data Index: 445622 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1696. Min Act: -0.0001

Data Index: 20316 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1791. Min Act: -0.0001

Data Index: 408528 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1819. Min Act: -0.0001

Data Index: 852040 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1754. Min Act: -0.0001

Data Index: 798324 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1674. Min Act: -0.0001

Data Index: 759836 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1738. Min Act: -0.0001

Data Index: 1458970 (Python Code)

Max Activating Token Index: 221

Text #15

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1275563 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1640. Min Act: -0.0001

Data Index: 592535 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1366. Min Act: -0.0001

Data Index: 1455193 (Python Code)

Max Activating Token Index: 825

Text #18

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1625. Min Act: -0.0001

Data Index: 532244 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1504. Min Act: -0.0001

Data Index: 958088 (C4 (Web Text))

Max Activating Token Index: 154