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

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

Neuron 1253 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2760. Min Act: -0.0000

Data Index: 457791 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2770. Min Act: -0.0000

Data Index: 657308 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2451. Min Act: -0.0001

Data Index: 581720 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2278. Min Act: -0.0000

Data Index: 834094 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2333. Min Act: -0.0001

Data Index: 458782 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2128. Min Act: -0.0001

Data Index: 648393 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2531. Min Act: -0.0000

Data Index: 977599 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2401. Min Act: -0.0000

Data Index: 330395 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1303809 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2461. Min Act: -0.0000

Data Index: 471891 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2425. Min Act: -0.0001

Data Index: 1004304 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2427. Min Act: -0.0000

Data Index: 833391 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1016239 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2323. Min Act: -0.0001

Data Index: 441981 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1231506 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2185. Min Act: -0.0001

Data Index: 810944 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2144. Min Act: -0.0000

Data Index: 606596 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2412. Min Act: -0.0001

Data Index: 95917 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2151. Min Act: -0.0000

Data Index: 212542 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2308. Min Act: -0.0001

Data Index: 769282 (C4 (Web Text))

Max Activating Token Index: 162