Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3745 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1945. Min Act: -0.0002

Data Index: 987545 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1776. Min Act: -0.0002

Data Index: 132805 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1739. Min Act: -0.0001

Data Index: 523540 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1535. Min Act: -0.0001

Data Index: 380255 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1439. Min Act: -0.0001

Data Index: 549142 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1537. Min Act: -0.0002

Data Index: 1354081 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1456. Min Act: -0.0001

Data Index: 195373 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1554. Min Act: -0.0001

Data Index: 171012 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1154. Min Act: -0.0001

Data Index: 424219 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1329. Min Act: -0.0002

Data Index: 777186 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1436. Min Act: -0.0002

Data Index: 196117 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1354. Min Act: -0.0002

Data Index: 66781 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1166623 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1313. Min Act: -0.0002

Data Index: 1333593 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1391. Min Act: -0.0001

Data Index: 1139838 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1276. Min Act: -0.0002

Data Index: 437054 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1329. Min Act: -0.0001

Data Index: 343548 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1332. Min Act: -0.0002

Data Index: 919152 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1381. Min Act: -0.0002

Data Index: 961889 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1012935 (C4 (Web Text))

Max Activating Token Index: 415