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

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

Neuron 4603 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7662. Min Range: -3.7662

Max Act: 3.7662. Min Act: -0.0000

Data Index: 1366802 (Python Code)

Max Activating Token Index: 317

Text #1

Max Range: 3.7662. Min Range: -3.7662

Max Act: 3.4498. Min Act: -0.0000

Data Index: 438231 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.8076. Min Act: -0.0000

Data Index: 631794 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.6231. Min Act: -0.0000

Data Index: 1451201 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.5722. Min Act: -0.0000

Data Index: 609991 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.4990. Min Act: -0.0000

Data Index: 1443037 (Python Code)

Max Activating Token Index: 972

Text #6

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.4521. Min Act: -0.0000

Data Index: 1523990 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.5620. Min Act: -0.0000

Data Index: 848392 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.2373. Min Act: -0.0000

Data Index: 1363494 (Python Code)

Max Activating Token Index: 819

Text #9

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.3511. Min Act: -0.0000

Data Index: 995903 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.6919. Min Act: -0.0000

Data Index: 1537573 (Python Code)

Max Activating Token Index: 326

Text #11

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.5021. Min Act: -0.0000

Data Index: 1392475 (Python Code)

Max Activating Token Index: 495

Text #12

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.2085. Min Act: -0.0000

Data Index: 794908 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.2469. Min Act: -0.0000

Data Index: 311540 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.2726. Min Act: -0.0000

Data Index: 1065125 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.2089. Min Act: -0.0000

Data Index: 232125 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 3.7662. Min Range: -3.7662

Max Act: 1.9928. Min Act: -0.0000

Data Index: 558151 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.1301. Min Act: -0.0000

Data Index: 202778 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.0189. Min Act: -0.0000

Data Index: 856903 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 3.7662. Min Range: -3.7662

Max Act: 2.0022. Min Act: -0.0000

Data Index: 1194803 (C4 (Web Text))

Max Activating Token Index: 439