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

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

Neuron 3638 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1916. Min Range: -1.1916

Max Act: 1.1916. Min Act: -0.0000

Data Index: 415767 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 1.1916. Min Range: -1.1916

Max Act: 1.0646. Min Act: -0.0000

Data Index: 245164 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 1.1916. Min Range: -1.1916

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1331626 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.9547. Min Act: -0.0000

Data Index: 868230 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1071860 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1272651 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1065160 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.9326. Min Act: -0.0000

Data Index: 648413 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.9183. Min Act: -0.0000

Data Index: 549367 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.8335. Min Act: -0.0000

Data Index: 205078 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.8627. Min Act: -0.0000

Data Index: 236998 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.8146. Min Act: -0.0000

Data Index: 829079 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.7868. Min Act: -0.0000

Data Index: 48057 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1331214 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.7993. Min Act: -0.0000

Data Index: 971462 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.7455. Min Act: -0.0000

Data Index: 192625 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1272168 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.7939. Min Act: -0.0000

Data Index: 325790 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1226352 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 1.1916. Min Range: -1.1916

Max Act: 0.7821. Min Act: -0.0000

Data Index: 90413 (C4 (Web Text))

Max Activating Token Index: 545