Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1454 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2182. Min Act: -0.0001

Data Index: 1317098 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1856. Min Act: -0.0001

Data Index: 94359 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1942. Min Act: -0.0001

Data Index: 22234 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1697. Min Act: -0.0001

Data Index: 498430 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1515. Min Act: -0.0001

Data Index: 896456 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1579. Min Act: -0.0001

Data Index: 709481 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1502. Min Act: -0.0001

Data Index: 325453 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1501. Min Act: -0.0001

Data Index: 429157 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1152711 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1495. Min Act: -0.0001

Data Index: 77598 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1348. Min Act: -0.0000

Data Index: 540912 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1491. Min Act: -0.0001

Data Index: 703123 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1372. Min Act: -0.0001

Data Index: 706040 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1375. Min Act: -0.0001

Data Index: 176589 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1362. Min Act: -0.0001

Data Index: 782952 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1386. Min Act: -0.0001

Data Index: 574240 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1358167 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1362. Min Act: -0.0001

Data Index: 643249 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1361. Min Act: -0.0001

Data Index: 460563 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1339. Min Act: -0.0001

Data Index: 462638 (C4 (Web Text))

Max Activating Token Index: 192