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

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

Neuron 5295 in Layer 0

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: 0.0483. Min Range: -0.0483

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1622769 (Python Code)

Max Activating Token Index: 101

Text #1

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0439. Min Act: -0.0001

Data Index: 829324 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0426. Min Act: -0.0001

Data Index: 866271 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1380495 (Python Code)

Max Activating Token Index: 634

Text #4

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0406. Min Act: -0.0001

Data Index: 1577953 (Python Code)

Max Activating Token Index: 832

Text #5

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1463591 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0393. Min Act: -0.0001

Data Index: 39336 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0390. Min Act: -0.0001

Data Index: 174624 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1469637 (Python Code)

Max Activating Token Index: 982

Text #9

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1473336 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0389. Min Act: -0.0001

Data Index: 1620322 (Python Code)

Max Activating Token Index: 502

Text #11

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0380. Min Act: -0.0001

Data Index: 1372455 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1223665 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0388. Min Act: -0.0001

Data Index: 1020237 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1531580 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0380. Min Act: -0.0001

Data Index: 1198961 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0374. Min Act: -0.0001

Data Index: 271415 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0374. Min Act: -0.0001

Data Index: 72938 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1650233 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0358. Min Act: -0.0001

Data Index: 495380 (C4 (Web Text))

Max Activating Token Index: 882