Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 474 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.2609. Min Act: -0.0000

Data Index: 1165399 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.3457. Min Act: -0.0000

Data Index: 1263076 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.2553. Min Act: -0.0000

Data Index: 68900 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.0822. Min Act: -0.0000

Data Index: 588890 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.2442. Min Act: -0.0000

Data Index: 396406 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.0582. Min Act: -0.0000

Data Index: 1122401 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.1005. Min Act: -0.0000

Data Index: 114426 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.0296. Min Act: -0.0000

Data Index: 284726 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.0917. Min Act: -0.0000

Data Index: 445942 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.0095. Min Act: -0.0000

Data Index: 1401048 (Python Code)

Max Activating Token Index: 824

Text #10

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.0677. Min Act: -0.0000

Data Index: 847604 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.0584. Min Act: -0.0000

Data Index: 907647 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.0016. Min Act: -0.0000

Data Index: 1310206 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 2.3457. Min Range: -2.3457

Max Act: 1.9793. Min Act: -0.0000

Data Index: 818201 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 2.3457. Min Range: -2.3457

Max Act: 1.9927. Min Act: -0.0000

Data Index: 343663 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 2.3457. Min Range: -2.3457

Max Act: 1.9829. Min Act: -0.0000

Data Index: 292241 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 2.3457. Min Range: -2.3457

Max Act: 1.9215. Min Act: -0.0000

Data Index: 562238 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.0362. Min Act: -0.0000

Data Index: 529510 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.0269. Min Act: -0.0000

Data Index: 1053813 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 2.3457. Min Range: -2.3457

Max Act: 2.0302. Min Act: -0.0000

Data Index: 453943 (C4 (Web Text))

Max Activating Token Index: 665