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

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

Neuron 3182 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: 0.7605. Min Range: -0.7605

Max Act: 0.6981. Min Act: -0.0000

Data Index: 770007 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1310997 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.7355. Min Act: -0.0001

Data Index: 460929 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.7107. Min Act: -0.0000

Data Index: 567279 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.7028. Min Act: -0.0000

Data Index: 727445 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.6292. Min Act: -0.0000

Data Index: 678058 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5288. Min Act: -0.0001

Data Index: 233393 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1303272 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1002194 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.6245. Min Act: -0.0000

Data Index: 579100 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1188031 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1298819 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1296932 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5574. Min Act: -0.0000

Data Index: 160805 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.6512. Min Act: -0.0000

Data Index: 703887 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5728. Min Act: -0.0000

Data Index: 881230 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5007. Min Act: -0.0000

Data Index: 397258 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5271. Min Act: -0.0000

Data Index: 681759 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1180102 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4779. Min Act: -0.0000

Data Index: 521371 (C4 (Web Text))

Max Activating Token Index: 818