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

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

Neuron 6025 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: 2.2353. Min Range: -2.2353

Max Act: 2.2353. Min Act: -0.0000

Data Index: 586182 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.9848. Min Act: -0.0000

Data Index: 603386 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.5961. Min Act: -0.0000

Data Index: 805360 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.7177. Min Act: -0.0000

Data Index: 1295829 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.5471. Min Act: -0.0000

Data Index: 1157419 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1349619 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.1120. Min Act: -0.0000

Data Index: 613936 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 2.2353. Min Range: -2.2353

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1060405 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.0766. Min Act: -0.0000

Data Index: 31124 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.0889. Min Act: -0.0000

Data Index: 1542433 (Python Code)

Max Activating Token Index: 321

Text #10

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.1190. Min Act: -0.0000

Data Index: 941013 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.0336. Min Act: -0.0000

Data Index: 76516 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.1056. Min Act: -0.0000

Data Index: 885611 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.0333. Min Act: -0.0000

Data Index: 593048 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 2.2353. Min Range: -2.2353

Max Act: 0.9708. Min Act: -0.0000

Data Index: 228540 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1564260 (Python Code)

Max Activating Token Index: 708

Text #16

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1502844 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.0126. Min Act: -0.0000

Data Index: 1405212 (Python Code)

Max Activating Token Index: 121

Text #18

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.0042. Min Act: -0.0000

Data Index: 1509608 (Python Code)

Max Activating Token Index: 347

Text #19

Max Range: 2.2353. Min Range: -2.2353

Max Act: 1.0735. Min Act: -0.0000

Data Index: 815408 (C4 (Web Text))

Max Activating Token Index: 262