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

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

Neuron 2928 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: 4.5002. Min Range: -4.5002

Max Act: 4.5002. Min Act: -0.0000

Data Index: 402130 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.9806. Min Act: -0.0000

Data Index: 563768 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.3757. Min Act: -0.0000

Data Index: 117047 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.5833. Min Act: -0.0000

Data Index: 1315164 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.4406. Min Act: -0.0000

Data Index: 557761 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.5430. Min Act: -0.0000

Data Index: 1340134 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.2589. Min Act: -0.0000

Data Index: 328228 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.3917. Min Act: -0.0000

Data Index: 878105 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.1777. Min Act: -0.0000

Data Index: 1103821 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.0236. Min Act: -0.0000

Data Index: 361112 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.1396. Min Act: -0.0000

Data Index: 625720 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.1944. Min Act: -0.0000

Data Index: 527252 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.4767. Min Act: -0.0000

Data Index: 71688 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.0239. Min Act: -0.0000

Data Index: 116383 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.0002. Min Act: -0.0000

Data Index: 1152630 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.0457. Min Act: -0.0000

Data Index: 693961 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.0015. Min Act: -0.0000

Data Index: 1102572 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 4.5002. Min Range: -4.5002

Max Act: 2.5411. Min Act: -0.0000

Data Index: 391463 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 4.5002. Min Range: -4.5002

Max Act: 2.7984. Min Act: -0.0000

Data Index: 931059 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 4.5002. Min Range: -4.5002

Max Act: 3.0491. Min Act: -0.0000

Data Index: 1189300 (C4 (Web Text))

Max Activating Token Index: 807