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

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

Neuron 5170 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1683. Min Range: -1.1683

Max Act: 1.1683. Min Act: -0.0000

Data Index: 58034 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 1.1683. Min Range: -1.1683

Max Act: 1.1677. Min Act: -0.0000

Data Index: 290832 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1322658 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9028. Min Act: -0.0000

Data Index: 416715 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.7865. Min Act: -0.0000

Data Index: 73603 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1159757 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8486. Min Act: -0.0000

Data Index: 411528 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8301. Min Act: -0.0000

Data Index: 97763 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.7777. Min Act: -0.0000

Data Index: 457983 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8008. Min Act: -0.0000

Data Index: 178335 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1331683 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.7337. Min Act: -0.0000

Data Index: 798036 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.7161. Min Act: -0.0000

Data Index: 502387 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1025658 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.6644. Min Act: -0.0000

Data Index: 976991 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.6992. Min Act: -0.0000

Data Index: 762010 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.6697. Min Act: -0.0000

Data Index: 91233 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.6744. Min Act: -0.0000

Data Index: 347422 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.6543. Min Act: -0.0000

Data Index: 859902 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.6439. Min Act: -0.0000

Data Index: 554411 (C4 (Web Text))

Max Activating Token Index: 160