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

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

Neuron 2635 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1548. Min Act: -0.0001

Data Index: 517921 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1741. Min Act: -0.0001

Data Index: 94923 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1379. Min Act: -0.0001

Data Index: 362056 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1507. Min Act: -0.0001

Data Index: 129995 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1102067 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1047797 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1410. Min Act: -0.0001

Data Index: 135846 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1261. Min Act: -0.0001

Data Index: 581119 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1317. Min Act: -0.0001

Data Index: 422249 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1359. Min Act: -0.0001

Data Index: 290626 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1453. Min Act: -0.0001

Data Index: 52763 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1267. Min Act: -0.0001

Data Index: 353297 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1082. Min Act: -0.0001

Data Index: 558585 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1304. Min Act: -0.0001

Data Index: 423961 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1233. Min Act: -0.0001

Data Index: 142022 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1050152 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1214. Min Act: -0.0001

Data Index: 257654 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1244. Min Act: -0.0001

Data Index: 704701 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1323. Min Act: -0.0001

Data Index: 782025 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1259. Min Act: -0.0001

Data Index: 193028 (C4 (Web Text))

Max Activating Token Index: 255