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

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

Neuron 422 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.5073. Min Act: -0.0000

Data Index: 763765 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1173343 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.1709. Min Act: -0.0000

Data Index: 320180 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0522. Min Act: -0.0000

Data Index: 644135 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0474. Min Act: -0.0000

Data Index: 786901 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0226. Min Act: -0.0000

Data Index: 1217731 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0902. Min Act: -0.0000

Data Index: 408489 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.5073. Min Range: -1.5073

Max Act: 0.9532. Min Act: -0.0000

Data Index: 342577 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0207. Min Act: -0.0000

Data Index: 1154095 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.5073. Min Range: -1.5073

Max Act: 0.9224. Min Act: -0.0000

Data Index: 180268 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0061. Min Act: -0.0000

Data Index: 726119 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 1.5073. Min Range: -1.5073

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1603005 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 1.5073. Min Range: -1.5073

Max Act: 0.9425. Min Act: -0.0000

Data Index: 77045 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0380. Min Act: -0.0000

Data Index: 88926 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 1.5073. Min Range: -1.5073

Max Act: 0.8636. Min Act: -0.0000

Data Index: 405802 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 1.5073. Min Range: -1.5073

Max Act: 0.9666. Min Act: -0.0000

Data Index: 262912 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 1.5073. Min Range: -1.5073

Max Act: 0.9614. Min Act: -0.0000

Data Index: 613440 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 1.5073. Min Range: -1.5073

Max Act: 0.8712. Min Act: -0.0000

Data Index: 544963 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 1.5073. Min Range: -1.5073

Max Act: 0.8635. Min Act: -0.0000

Data Index: 118985 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 1.5073. Min Range: -1.5073

Max Act: 0.9116. Min Act: -0.0000

Data Index: 901138 (C4 (Web Text))

Max Activating Token Index: 645