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

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

Neuron 3163 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: 0.7835. Min Range: -0.7835

Max Act: 0.7835. Min Act: -0.0000

Data Index: 686802 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6355. Min Act: -0.0000

Data Index: 519620 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6252. Min Act: -0.0000

Data Index: 560658 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6180. Min Act: -0.0000

Data Index: 663017 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5754. Min Act: -0.0000

Data Index: 97896 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5899. Min Act: -0.0000

Data Index: 415571 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1309956 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1163488 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5841. Min Act: -0.0000

Data Index: 408315 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5407. Min Act: -0.0000

Data Index: 468969 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1206224 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5298. Min Act: -0.0000

Data Index: 658924 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1013574 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5357. Min Act: -0.0000

Data Index: 657435 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5089. Min Act: -0.0000

Data Index: 672284 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5186. Min Act: -0.0000

Data Index: 518119 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5029. Min Act: -0.0000

Data Index: 790262 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5324. Min Act: -0.0000

Data Index: 665309 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5279. Min Act: -0.0000

Data Index: 25060 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4897. Min Act: -0.0000

Data Index: 165380 (C4 (Web Text))

Max Activating Token Index: 454