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

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

Neuron 2314 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1457. Min Range: -2.1457

Max Act: 2.1457. Min Act: -0.0000

Data Index: 795545 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.8216. Min Act: -0.0000

Data Index: 688206 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.8740. Min Act: -0.0000

Data Index: 1290306 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.4168. Min Act: -0.0000

Data Index: 898917 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.2360. Min Act: -0.0000

Data Index: 601589 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.1703. Min Act: -0.0000

Data Index: 360237 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.0849. Min Act: -0.0000

Data Index: 125522 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.1411. Min Act: -0.0000

Data Index: 837562 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.1867. Min Act: -0.0000

Data Index: 1100695 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.1067. Min Act: -0.0000

Data Index: 815815 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.0404. Min Act: -0.0000

Data Index: 272392 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.0187. Min Act: -0.0000

Data Index: 138929 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 2.1457. Min Range: -2.1457

Max Act: 0.9784. Min Act: -0.0000

Data Index: 606972 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 2.1457. Min Range: -2.1457

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1414835 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.0298. Min Act: -0.0000

Data Index: 886681 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 2.1457. Min Range: -2.1457

Max Act: 0.9904. Min Act: -0.0000

Data Index: 192178 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.0303. Min Act: -0.0000

Data Index: 264739 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 2.1457. Min Range: -2.1457

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1079308 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 2.1457. Min Range: -2.1457

Max Act: 1.0321. Min Act: -0.0000

Data Index: 970959 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 2.1457. Min Range: -2.1457

Max Act: 0.8886. Min Act: -0.0000

Data Index: 66639 (C4 (Web Text))

Max Activating Token Index: 592