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

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

Neuron 3458 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.5640. Min Act: -0.0000

Data Index: 1307352 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.5005. Min Act: -0.0000

Data Index: 1250363 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.5037. Min Act: -0.0000

Data Index: 336357 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.4117. Min Act: -0.0000

Data Index: 771314 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3722. Min Act: -0.0000

Data Index: 320100 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3593. Min Act: -0.0000

Data Index: 1112727 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.4203. Min Act: -0.0000

Data Index: 1273899 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3250. Min Act: -0.0000

Data Index: 686219 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3217. Min Act: -0.0000

Data Index: 109455 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3170. Min Act: -0.0000

Data Index: 368338 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.2911. Min Act: -0.0000

Data Index: 588556 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.4213. Min Act: -0.0000

Data Index: 767177 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3433. Min Act: -0.0000

Data Index: 544114 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.2467. Min Act: -0.0000

Data Index: 661774 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1242262 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.2094. Min Act: -0.0000

Data Index: 771426 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.1991. Min Act: -0.0000

Data Index: 142261 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.2023. Min Act: -0.0000

Data Index: 668046 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.2779. Min Act: -0.0000

Data Index: 661508 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.2678. Min Act: -0.0000

Data Index: 1321480 (C4 (Web Text))

Max Activating Token Index: 277