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

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

Neuron 3782 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.4502. Min Act: -0.0001

Data Index: 1157314 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.3623. Min Act: -0.0001

Data Index: 108725 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.3867. Min Act: -0.0001

Data Index: 582276 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.3514. Min Act: -0.0001

Data Index: 1096451 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.4886. Min Act: -0.0001

Data Index: 854939 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.3476. Min Act: -0.0001

Data Index: 335111 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1698. Min Act: -0.0001

Data Index: 680871 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.4532. Min Act: -0.0001

Data Index: 773879 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.3336. Min Act: -0.0001

Data Index: 1269262 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2051. Min Act: -0.0001

Data Index: 1171448 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2824. Min Act: -0.0001

Data Index: 129073 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2003. Min Act: -0.0001

Data Index: 647525 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2591. Min Act: -0.0001

Data Index: 1124433 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2047. Min Act: -0.0001

Data Index: 1319248 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0474. Min Act: -0.0001

Data Index: 332669 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2491. Min Act: -0.0001

Data Index: 1199613 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1324. Min Act: -0.0001

Data Index: 1198230 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2074. Min Act: -0.0001

Data Index: 180115 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1152. Min Act: -0.0001

Data Index: 36086 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1849. Min Act: -0.0001

Data Index: 27178 (C4 (Web Text))

Max Activating Token Index: 424