Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4761 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.3207. Min Range: -6.3207

Max Act: 6.3207. Min Act: -0.0000

Data Index: 1006160 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 6.3207. Min Range: -6.3207

Max Act: 6.0348. Min Act: -0.0000

Data Index: 679208 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 6.3207. Min Range: -6.3207

Max Act: 6.0296. Min Act: -0.0000

Data Index: 186080 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 6.3207. Min Range: -6.3207

Max Act: 5.7767. Min Act: -0.0000

Data Index: 1613573 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 6.3207. Min Range: -6.3207

Max Act: 5.5489. Min Act: -0.0000

Data Index: 675633 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 6.3207. Min Range: -6.3207

Max Act: 5.3845. Min Act: -0.0000

Data Index: 75918 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 6.3207. Min Range: -6.3207

Max Act: 5.4649. Min Act: -0.0000

Data Index: 1249359 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 6.3207. Min Range: -6.3207

Max Act: 5.2369. Min Act: -0.0000

Data Index: 366846 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 6.3207. Min Range: -6.3207

Max Act: 5.2195. Min Act: -0.0000

Data Index: 243782 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 6.3207. Min Range: -6.3207

Max Act: 4.8122. Min Act: -0.0000

Data Index: 772812 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 6.3207. Min Range: -6.3207

Max Act: 5.1032. Min Act: -0.0000

Data Index: 61938 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 6.3207. Min Range: -6.3207

Max Act: 5.0829. Min Act: 0.0000

Data Index: 443526 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 6.3207. Min Range: -6.3207

Max Act: 4.7386. Min Act: -0.0000

Data Index: 306136 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 6.3207. Min Range: -6.3207

Max Act: 4.9072. Min Act: -0.0000

Data Index: 549976 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 6.3207. Min Range: -6.3207

Max Act: 4.7279. Min Act: -0.0000

Data Index: 922047 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 6.3207. Min Range: -6.3207

Max Act: 4.7013. Min Act: 0.0004

Data Index: 394183 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 6.3207. Min Range: -6.3207

Max Act: 4.8737. Min Act: 0.0001

Data Index: 1325493 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 6.3207. Min Range: -6.3207

Max Act: 4.8385. Min Act: 0.0004

Data Index: 795623 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 6.3207. Min Range: -6.3207

Max Act: 5.2167. Min Act: -0.0000

Data Index: 1247341 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 6.3207. Min Range: -6.3207

Max Act: 4.7757. Min Act: -0.0000

Data Index: 785934 (C4 (Web Text))

Max Activating Token Index: 408