Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3253 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.3857. Min Act: -0.0001

Data Index: 235171 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4305. Min Act: -0.0000

Data Index: 880150 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4474. Min Act: -0.0001

Data Index: 56717 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4833. Min Act: -0.0001

Data Index: 703380 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4428. Min Act: -0.0001

Data Index: 800662 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4244. Min Act: -0.0001

Data Index: 452709 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4011. Min Act: -0.0001

Data Index: 151559 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.3994. Min Act: -0.0001

Data Index: 678585 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4164. Min Act: -0.0001

Data Index: 607220 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4030. Min Act: -0.0001

Data Index: 454414 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4106. Min Act: -0.0001

Data Index: 505697 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4130. Min Act: -0.0001

Data Index: 12962 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.3982. Min Act: -0.0000

Data Index: 639979 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.3866. Min Act: -0.0000

Data Index: 189012 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4220. Min Act: -0.0001

Data Index: 1029132 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.3962. Min Act: -0.0000

Data Index: 184536 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4160. Min Act: -0.0000

Data Index: 859928 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.3621. Min Act: -0.0001

Data Index: 205129 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.3710. Min Act: -0.0001

Data Index: 1025240 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.3952. Min Act: -0.0001

Data Index: 1345239 (C4 (Web Text))

Max Activating Token Index: 546