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

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

Neuron 3630 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.8834. Min Act: -0.0000

Data Index: 328367 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.9850. Min Act: -0.0000

Data Index: 907201 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.7577. Min Act: -0.0000

Data Index: 400209 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.9542. Min Act: -0.0000

Data Index: 579364 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.8356. Min Act: -0.0000

Data Index: 295444 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.8264. Min Act: -0.0000

Data Index: 684433 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.8428. Min Act: -0.0000

Data Index: 478702 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.7374. Min Act: -0.0000

Data Index: 541949 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.8746. Min Act: -0.0000

Data Index: 1056927 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.7673. Min Act: -0.0000

Data Index: 34195 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.7436. Min Act: -0.0000

Data Index: 490684 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.8091. Min Act: -0.0000

Data Index: 1165030 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.8228. Min Act: -0.0000

Data Index: 291819 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.8078. Min Act: -0.0000

Data Index: 777841 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.6981. Min Act: -0.0000

Data Index: 614947 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.6145. Min Act: -0.0000

Data Index: 204617 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.7031. Min Act: -0.0000

Data Index: 975720 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.6154. Min Act: -0.0000

Data Index: 679623 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.6641. Min Act: -0.0000

Data Index: 420334 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.8520. Min Act: -0.0000

Data Index: 136911 (C4 (Web Text))

Max Activating Token Index: 85