Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1175 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0027. Min Range: -4.0027

Max Act: 4.0027. Min Act: -0.0000

Data Index: 408034 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.9571. Min Act: -0.0000

Data Index: 215456 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.0956. Min Act: -0.0000

Data Index: 826699 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.1272. Min Act: -0.0000

Data Index: 971090 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.9141. Min Act: -0.0000

Data Index: 707214 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.8144. Min Act: -0.0000

Data Index: 1188808 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.6802. Min Act: -0.0000

Data Index: 585445 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.5278. Min Act: -0.0000

Data Index: 982752 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.5020. Min Act: -0.0000

Data Index: 1202437 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.3411. Min Act: -0.0000

Data Index: 848940 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.3232. Min Act: -0.0000

Data Index: 768052 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.5471. Min Act: -0.0000

Data Index: 550 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.3443. Min Act: -0.0000

Data Index: 304144 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.2815. Min Act: -0.0000

Data Index: 1150054 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.0306. Min Act: -0.0000

Data Index: 377149 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.2394. Min Act: -0.0000

Data Index: 1193704 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.1315. Min Act: -0.0000

Data Index: 1164867 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.0913. Min Act: -0.0000

Data Index: 1294013 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 4.0027. Min Range: -4.0027

Max Act: 1.9622. Min Act: -0.0000

Data Index: 1206330 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.0889. Min Act: -0.0000

Data Index: 690723 (C4 (Web Text))

Max Activating Token Index: 383