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

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

Neuron 1741 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: 0.6164. Min Range: -0.6164

Max Act: 0.6164. Min Act: -0.0001

Data Index: 333139 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4808. Min Act: -0.0001

Data Index: 440313 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5462. Min Act: -0.0001

Data Index: 250698 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5312. Min Act: -0.0000

Data Index: 27082 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4927. Min Act: -0.0001

Data Index: 45601 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5049. Min Act: -0.0001

Data Index: 1285654 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5097. Min Act: -0.0001

Data Index: 1064562 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4586. Min Act: -0.0000

Data Index: 829923 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4725. Min Act: -0.0001

Data Index: 1147501 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4915. Min Act: -0.0001

Data Index: 890419 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4501. Min Act: -0.0000

Data Index: 681467 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4608. Min Act: -0.0001

Data Index: 191688 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4395. Min Act: -0.0001

Data Index: 249592 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4852. Min Act: -0.0000

Data Index: 545567 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4671. Min Act: -0.0000

Data Index: 924604 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4495. Min Act: -0.0001

Data Index: 1457494 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4233. Min Act: -0.0000

Data Index: 188132 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4221. Min Act: -0.0001

Data Index: 666264 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4704. Min Act: -0.0001

Data Index: 181671 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4012. Min Act: -0.0000

Data Index: 665517 (C4 (Web Text))

Max Activating Token Index: 266