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

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

Neuron 2524 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1202. Min Range: -1.1202

Max Act: 1.1202. Min Act: -0.0000

Data Index: 5035 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 1.1202. Min Range: -1.1202

Max Act: 1.0882. Min Act: -0.0000

Data Index: 216260 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8301. Min Act: -0.0000

Data Index: 61015 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.9286. Min Act: -0.0000

Data Index: 424046 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8848. Min Act: -0.0000

Data Index: 447196 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8621. Min Act: -0.0000

Data Index: 273183 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8524. Min Act: -0.0000

Data Index: 256347 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8663. Min Act: -0.0000

Data Index: 272449 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.7628. Min Act: -0.0000

Data Index: 659924 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8405. Min Act: -0.0000

Data Index: 64929 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8397. Min Act: -0.0000

Data Index: 469316 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1138515 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1199175 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8324. Min Act: -0.0000

Data Index: 209479 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8809. Min Act: -0.0000

Data Index: 663332 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8648. Min Act: -0.0000

Data Index: 975419 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.7939. Min Act: -0.0000

Data Index: 440465 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8186. Min Act: -0.0000

Data Index: 768724 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1257137 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8197. Min Act: -0.0000

Data Index: 809145 (C4 (Web Text))

Max Activating Token Index: 788