Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 523 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.5541. Min Act: -0.0001

Data Index: 782652 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.5542. Min Act: -0.0000

Data Index: 525788 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1029347 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.5086. Min Act: -0.0001

Data Index: 357893 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4476. Min Act: -0.0001

Data Index: 611379 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4512. Min Act: -0.0000

Data Index: 229865 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1262384 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4855. Min Act: -0.0001

Data Index: 1257960 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4393. Min Act: -0.0001

Data Index: 1107325 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4352. Min Act: -0.0000

Data Index: 595719 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4334. Min Act: -0.0001

Data Index: 1636121 (Python Code)

Max Activating Token Index: 106

Text #11

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4448. Min Act: -0.0000

Data Index: 50767 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4297. Min Act: -0.0000

Data Index: 110334 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4403. Min Act: -0.0000

Data Index: 406153 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4346. Min Act: -0.0001

Data Index: 1313751 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4113. Min Act: -0.0000

Data Index: 386994 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1104699 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4071. Min Act: -0.0001

Data Index: 918788 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3880. Min Act: -0.0001

Data Index: 202820 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4012. Min Act: -0.0001

Data Index: 1431144 (Python Code)

Max Activating Token Index: 208