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

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

Neuron 3074 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: 0.2444. Min Range: -0.2444

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1349605 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2000. Min Act: 0.0000

Data Index: 1310590 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1961. Min Act: 0.0001

Data Index: 857074 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1078173 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1717. Min Act: -0.0000

Data Index: 404390 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1989. Min Act: -0.0000

Data Index: 653050 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1820. Min Act: -0.0000

Data Index: 600827 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1892. Min Act: -0.0000

Data Index: 917891 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1780. Min Act: -0.0000

Data Index: 993028 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1788. Min Act: -0.0000

Data Index: 520729 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1502045 (Python Code)

Max Activating Token Index: 339

Text #11

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1163076 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1766. Min Act: -0.0000

Data Index: 588893 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1610. Min Act: -0.0000

Data Index: 596617 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1258297 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1668. Min Act: 0.0000

Data Index: 1299195 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1564. Min Act: -0.0000

Data Index: 518548 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1833. Min Act: -0.0000

Data Index: 876861 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1107321 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1544. Min Act: -0.0000

Data Index: 602260 (C4 (Web Text))

Max Activating Token Index: 407