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

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

Neuron 1535 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: 3.5384. Min Range: -3.5384

Max Act: 3.5125. Min Act: -0.0000

Data Index: 653020 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.2853. Min Act: -0.0000

Data Index: 1239536 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.5384. Min Act: -0.0000

Data Index: 830464 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.0905. Min Act: -0.0000

Data Index: 362799 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4899. Min Act: -0.0000

Data Index: 643987 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.3441. Min Act: -0.0000

Data Index: 927672 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4302. Min Act: -0.0000

Data Index: 119875 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.1094. Min Act: -0.0000

Data Index: 163535 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.1229. Min Act: -0.0000

Data Index: 256383 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.2163. Min Act: -0.0000

Data Index: 1215198 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 3.5384. Min Range: -3.5384

Max Act: 2.9975. Min Act: -0.0000

Data Index: 713569 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.1743. Min Act: -0.0000

Data Index: 233290 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.1332. Min Act: -0.0000

Data Index: 1335340 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.1078. Min Act: -0.0000

Data Index: 984318 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.1161. Min Act: -0.0000

Data Index: 1091140 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.1114. Min Act: -0.0000

Data Index: 970585 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 3.5384. Min Range: -3.5384

Max Act: 2.9407. Min Act: -0.0000

Data Index: 629850 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.0979. Min Act: -0.0000

Data Index: 1303162 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 3.5384. Min Range: -3.5384

Max Act: 2.9106. Min Act: -0.0000

Data Index: 1148751 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.0415. Min Act: -0.0000

Data Index: 1202858 (C4 (Web Text))

Max Activating Token Index: 737