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

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

Neuron 5411 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: 2.5812. Min Range: -2.5812

Max Act: 2.5812. Min Act: -0.0000

Data Index: 1155425 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.3944. Min Act: 0.0000

Data Index: 581369 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.2505. Min Act: -0.0000

Data Index: 1645156 (Python Code)

Max Activating Token Index: 802

Text #3

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.4404. Min Act: -0.0000

Data Index: 89002 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.3309. Min Act: -0.0000

Data Index: 704399 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.2530. Min Act: -0.0000

Data Index: 1182718 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.0969. Min Act: -0.0000

Data Index: 747741 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.0708. Min Act: -0.0000

Data Index: 883603 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.2872. Min Act: -0.0000

Data Index: 1181623 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.1304. Min Act: -0.0000

Data Index: 360825 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.1539. Min Act: -0.0000

Data Index: 1425385 (Python Code)

Max Activating Token Index: 838

Text #11

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.1193. Min Act: -0.0000

Data Index: 1367963 (Python Code)

Max Activating Token Index: 457

Text #12

Max Range: 2.5812. Min Range: -2.5812

Max Act: 1.9502. Min Act: -0.0000

Data Index: 589012 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.0712. Min Act: -0.0000

Data Index: 1548246 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.0629. Min Act: -0.0000

Data Index: 809988 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 2.5812. Min Range: -2.5812

Max Act: 1.9478. Min Act: -0.0000

Data Index: 446800 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.0506. Min Act: -0.0000

Data Index: 446324 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 2.5812. Min Range: -2.5812

Max Act: 2.0155. Min Act: -0.0000

Data Index: 649543 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 2.5812. Min Range: -2.5812

Max Act: 1.9748. Min Act: -0.0000

Data Index: 679586 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 2.5812. Min Range: -2.5812

Max Act: 1.9272. Min Act: -0.0000

Data Index: 1585237 (Python Code)

Max Activating Token Index: 851