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

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

Neuron 1125 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.4876. Min Act: -0.0000

Data Index: 114328 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.4337. Min Act: -0.0000

Data Index: 897604 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.3932. Min Act: -0.0000

Data Index: 910958 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.2595. Min Act: -0.0000

Data Index: 910915 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.2231. Min Act: -0.0000

Data Index: 767499 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.1424. Min Act: -0.0000

Data Index: 1639328 (Python Code)

Max Activating Token Index: 655

Text #6

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.0979. Min Act: -0.0000

Data Index: 460804 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1324052 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.1283. Min Act: -0.0000

Data Index: 692009 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1069089 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.1350. Min Act: -0.0000

Data Index: 20223 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.1180. Min Act: -0.0000

Data Index: 117627 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.0494. Min Act: -0.0000

Data Index: 233441 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1177723 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.0075. Min Act: -0.0000

Data Index: 55188 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.1409. Min Act: -0.0000

Data Index: 875624 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1043976 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 1.4876. Min Range: -1.4876

Max Act: 1.0153. Min Act: -0.0000

Data Index: 674525 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 1.4876. Min Range: -1.4876

Max Act: 0.8784. Min Act: -0.0000

Data Index: 605532 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 1.4876. Min Range: -1.4876

Max Act: 0.8950. Min Act: -0.0000

Data Index: 21151 (C4 (Web Text))

Max Activating Token Index: 824