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

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

Neuron 3967 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.9826. Min Act: -0.0000

Data Index: 339933 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.9539. Min Act: -0.0000

Data Index: 585947 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.9112. Min Act: -0.0000

Data Index: 235070 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.9318. Min Act: -0.0000

Data Index: 883086 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.8418. Min Act: 0.0001

Data Index: 1244303 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1007650 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.8427. Min Act: -0.0000

Data Index: 278216 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1255534 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7974. Min Act: -0.0000

Data Index: 55165 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7678. Min Act: -0.0000

Data Index: 323206 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.8005. Min Act: -0.0000

Data Index: 504566 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1138388 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7905. Min Act: -0.0000

Data Index: 466879 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7723. Min Act: -0.0000

Data Index: 571706 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7248. Min Act: -0.0000

Data Index: 152445 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7327. Min Act: 0.0000

Data Index: 770667 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6971. Min Act: -0.0000

Data Index: 873458 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6923. Min Act: -0.0000

Data Index: 612682 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7196. Min Act: -0.0000

Data Index: 943749 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6490. Min Act: -0.0000

Data Index: 345080 (C4 (Web Text))

Max Activating Token Index: 24