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

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

Neuron 1378 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.6173. Min Act: -0.0000

Data Index: 708190 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.5669. Min Act: -0.0000

Data Index: 793217 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.5929. Min Act: -0.0000

Data Index: 878780 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.5876. Min Act: -0.0000

Data Index: 675393 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.2907. Min Act: -0.0000

Data Index: 242280 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.2439. Min Act: -0.0000

Data Index: 919807 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.1961. Min Act: -0.0000

Data Index: 1314960 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.3102. Min Act: -0.0000

Data Index: 279497 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.2097. Min Act: -0.0000

Data Index: 277288 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.1958. Min Act: -0.0000

Data Index: 972125 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.1893. Min Act: -0.0000

Data Index: 1293116 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.1231. Min Act: -0.0000

Data Index: 1302284 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.3647. Min Act: -0.0000

Data Index: 1174012 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.2155. Min Act: -0.0000

Data Index: 921929 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.1967. Min Act: -0.0000

Data Index: 561940 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.1386. Min Act: -0.0000

Data Index: 264603 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.0891. Min Act: -0.0000

Data Index: 1120860 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.1216. Min Act: -0.0000

Data Index: 1283167 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.3013. Min Act: -0.0000

Data Index: 747944 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 2.6173. Min Range: -2.6173

Max Act: 2.1129. Min Act: -0.0000

Data Index: 687008 (C4 (Web Text))

Max Activating Token Index: 207