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

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

Neuron 5981 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1600405 (Python Code)

Max Activating Token Index: 1017

Text #1

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1638732 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.6202. Min Act: -0.0000

Data Index: 913598 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1608966 (Python Code)

Max Activating Token Index: 643

Text #4

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5104. Min Act: -0.0000

Data Index: 583256 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4500. Min Act: -0.0000

Data Index: 708060 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1318661 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4964. Min Act: -0.0000

Data Index: 923789 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1194508 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1565283 (Python Code)

Max Activating Token Index: 824

Text #10

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1080270 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4816. Min Act: 0.0000

Data Index: 429735 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4491. Min Act: -0.0000

Data Index: 509882 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4731. Min Act: -0.0000

Data Index: 85176 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4639. Min Act: -0.0000

Data Index: 790718 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1217715 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1000806 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4420. Min Act: -0.0000

Data Index: 192254 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1655010 (Python Code)

Max Activating Token Index: 950

Text #19

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4319. Min Act: -0.0000

Data Index: 715855 (C4 (Web Text))

Max Activating Token Index: 515