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

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

Neuron 3535 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3516. Min Range: -2.3516

Max Act: 2.3516. Min Act: -0.0000

Data Index: 852532 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 2.3516. Min Range: -2.3516

Max Act: 2.3331. Min Act: -0.0000

Data Index: 203798 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 2.3516. Min Range: -2.3516

Max Act: 2.1213. Min Act: -0.0000

Data Index: 1184486 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.8653. Min Act: -0.0000

Data Index: 1120319 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.8587. Min Act: -0.0000

Data Index: 530203 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.8447. Min Act: -0.0000

Data Index: 379047 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.8152. Min Act: -0.0000

Data Index: 1316858 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.9315. Min Act: -0.0000

Data Index: 557432 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.7514. Min Act: -0.0000

Data Index: 26374 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.8509. Min Act: -0.0000

Data Index: 426007 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.7334. Min Act: -0.0000

Data Index: 1257019 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.8323. Min Act: -0.0000

Data Index: 592891 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.7077. Min Act: -0.0000

Data Index: 162618 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.7021. Min Act: -0.0000

Data Index: 1063876 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.7892. Min Act: -0.0000

Data Index: 1347701 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.6894. Min Act: -0.0000

Data Index: 298956 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.6839. Min Act: -0.0000

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.6554. Min Act: -0.0000

Data Index: 585183 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.6552. Min Act: -0.0000

Data Index: 1331168 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 2.3516. Min Range: -2.3516

Max Act: 1.6460. Min Act: -0.0000

Data Index: 698941 (C4 (Web Text))

Max Activating Token Index: 442