Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 581 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0002

Data Index: 516979 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0301. Min Act: -0.0002

Data Index: 114532 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0291. Min Act: -0.0002

Data Index: 28053 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1411696 (Python Code)

Max Activating Token Index: 185

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1426787 (Python Code)

Max Activating Token Index: 901

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0275. Min Act: -0.0002

Data Index: 871729 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1295264 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1540910 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1228527 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0267. Min Act: -0.0002

Data Index: 912490 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0270. Min Act: -0.0002

Data Index: 346818 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0258. Min Act: -0.0002

Data Index: 83900 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1446245 (Python Code)

Max Activating Token Index: 95

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1517598 (Python Code)

Max Activating Token Index: 854

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0260. Min Act: -0.0002

Data Index: 511320 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1571413 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1240798 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0249. Min Act: -0.0002

Data Index: 907428 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1074990 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1474908 (Python Code)

Max Activating Token Index: 883