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

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

Neuron 4423 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6894. Min Range: -2.6894

Max Act: 2.6894. Min Act: -0.0000

Data Index: 636636 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 2.6894. Min Range: -2.6894

Max Act: 2.2414. Min Act: -0.0000

Data Index: 226740 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 2.6894. Min Range: -2.6894

Max Act: 2.1826. Min Act: -0.0000

Data Index: 1328550 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 2.6894. Min Range: -2.6894

Max Act: 2.0563. Min Act: -0.0000

Data Index: 104228 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 2.6894. Min Range: -2.6894

Max Act: 2.0793. Min Act: -0.0000

Data Index: 253105 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.8635. Min Act: -0.0000

Data Index: 1221949 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.8409. Min Act: -0.0000

Data Index: 1170485 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.9268. Min Act: -0.0000

Data Index: 303231 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.9116. Min Act: -0.0000

Data Index: 117856 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.9006. Min Act: -0.0000

Data Index: 395861 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.8892. Min Act: -0.0000

Data Index: 970812 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.8721. Min Act: -0.0000

Data Index: 1241186 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.8014. Min Act: -0.0000

Data Index: 538840 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.7827. Min Act: -0.0000

Data Index: 1159607 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.7312. Min Act: -0.0000

Data Index: 440080 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.7445. Min Act: -0.0000

Data Index: 1323784 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.7441. Min Act: -0.0000

Data Index: 609466 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.7899. Min Act: -0.0000

Data Index: 244566 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.7801. Min Act: -0.0000

Data Index: 432714 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 2.6894. Min Range: -2.6894

Max Act: 1.6796. Min Act: -0.0000

Data Index: 1170789 (C4 (Web Text))

Max Activating Token Index: 224