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

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

Neuron 4448 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2045. Min Range: -1.2045

Max Act: 1.2045. Min Act: -0.0001

Data Index: 805251 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 1.2045. Min Range: -1.2045

Max Act: 1.0319. Min Act: -0.0001

Data Index: 975327 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.9569. Min Act: -0.0001

Data Index: 203910 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.9732. Min Act: -0.0001

Data Index: 590448 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.9364. Min Act: -0.0001

Data Index: 144969 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.9722. Min Act: -0.0001

Data Index: 876371 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.8912. Min Act: -0.0001

Data Index: 884052 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.9013. Min Act: -0.0001

Data Index: 33506 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.9046. Min Act: -0.0001

Data Index: 95806 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.9272. Min Act: -0.0001

Data Index: 896647 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.7643. Min Act: -0.0001

Data Index: 1230316 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.7470. Min Act: -0.0001

Data Index: 285615 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.7297. Min Act: -0.0001

Data Index: 766577 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.8169. Min Act: -0.0001

Data Index: 1229555 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.7582. Min Act: -0.0001

Data Index: 643273 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.8071. Min Act: -0.0001

Data Index: 635019 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.7458. Min Act: -0.0001

Data Index: 770777 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.7167. Min Act: -0.0001

Data Index: 1130620 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.7647. Min Act: -0.0001

Data Index: 664006 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.7121. Min Act: -0.0001

Data Index: 693652 (C4 (Web Text))

Max Activating Token Index: 289