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

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

Neuron 3900 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.4271. Min Act: -0.0001

Data Index: 5753 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.3950. Min Act: -0.0001

Data Index: 403567 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.2875. Min Act: -0.0000

Data Index: 430407 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.3458. Min Act: -0.0000

Data Index: 1370431 (Python Code)

Max Activating Token Index: 121

Text #4

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.2373. Min Act: -0.0000

Data Index: 325095 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.2980. Min Act: -0.0000

Data Index: 1398274 (Python Code)

Max Activating Token Index: 647

Text #6

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.1839. Min Act: -0.0001

Data Index: 921079 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1403586 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1531520 (Python Code)

Max Activating Token Index: 963

Text #9

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.1562. Min Act: -0.0000

Data Index: 1578490 (Python Code)

Max Activating Token Index: 341

Text #10

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.0755. Min Act: -0.0000

Data Index: 15364 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.1381. Min Act: -0.0000

Data Index: 230635 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.1392. Min Act: -0.0000

Data Index: 638290 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.1261. Min Act: -0.0001

Data Index: 1007329 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.1221. Min Act: -0.0000

Data Index: 850779 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.0494. Min Act: -0.0000

Data Index: 727899 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.1150. Min Act: -0.0000

Data Index: 419676 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.0797. Min Act: -0.0001

Data Index: 11941 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1299997 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 1.4271. Min Range: -1.4271

Max Act: 1.0201. Min Act: -0.0001

Data Index: 627191 (C4 (Web Text))

Max Activating Token Index: 975