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

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

Neuron 2366 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.5890. Min Act: -0.0000

Data Index: 30828 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.5458. Min Act: -0.0000

Data Index: 551019 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.5574. Min Act: -0.0001

Data Index: 987201 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.5719. Min Act: -0.0001

Data Index: 920994 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.5317. Min Act: -0.0000

Data Index: 617922 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.5321. Min Act: -0.0001

Data Index: 474835 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.5271. Min Act: -0.0001

Data Index: 1153391 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4774. Min Act: -0.0000

Data Index: 617183 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4938. Min Act: -0.0000

Data Index: 365080 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4709. Min Act: -0.0001

Data Index: 311585 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4717. Min Act: -0.0000

Data Index: 300465 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4323. Min Act: -0.0001

Data Index: 1147512 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4403. Min Act: -0.0000

Data Index: 380923 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1139559 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4732. Min Act: -0.0001

Data Index: 11215 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1037197 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1006571 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4379. Min Act: -0.0001

Data Index: 735926 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4295. Min Act: -0.0000

Data Index: 916667 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3860. Min Act: -0.0000

Data Index: 115526 (C4 (Web Text))

Max Activating Token Index: 785