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

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

Neuron 4088 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.6060. Min Act: -0.0000

Data Index: 1354301 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.5442. Min Act: -0.0000

Data Index: 183434 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.4459. Min Act: 0.0000

Data Index: 585369 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.2076. Min Act: 0.0000

Data Index: 781946 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.1794. Min Act: -0.0000

Data Index: 1034381 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.2820. Min Act: 0.0000

Data Index: 226851 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.0621. Min Act: 0.0000

Data Index: 807611 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.9547. Min Act: -0.0000

Data Index: 261245 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.0637. Min Act: 0.0000

Data Index: 393246 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.6966. Min Act: -0.0000

Data Index: 795450 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.7282. Min Act: -0.0000

Data Index: 887919 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.6904. Min Act: 0.0000

Data Index: 1045637 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.6638. Min Act: -0.0000

Data Index: 1004298 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.6569. Min Act: 0.0000

Data Index: 712551 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.6265. Min Act: -0.0000

Data Index: 366970 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.5987. Min Act: 0.0001

Data Index: 445893 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.4126. Min Act: 0.0000

Data Index: 144174 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.6111. Min Act: -0.0000

Data Index: 588931 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.4725. Min Act: -0.0000

Data Index: 1197608 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 3.6060. Min Range: -3.6060

Max Act: 2.4151. Min Act: -0.0000

Data Index: 1005096 (C4 (Web Text))

Max Activating Token Index: 772