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

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

Neuron 5784 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.6340. Min Act: -0.0001

Data Index: 736232 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.7492. Min Act: -0.0001

Data Index: 72658 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.6115. Min Act: -0.0001

Data Index: 798727 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.5733. Min Act: -0.0001

Data Index: 571254 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.5326. Min Act: -0.0001

Data Index: 1182693 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.4460. Min Act: -0.0001

Data Index: 273472 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2440. Min Act: -0.0001

Data Index: 549841 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2798. Min Act: -0.0001

Data Index: 789451 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0737. Min Act: -0.0001

Data Index: 1328683 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2228. Min Act: -0.0001

Data Index: 463874 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2959. Min Act: -0.0001

Data Index: 19518 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.3225. Min Act: -0.0001

Data Index: 1140518 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2447. Min Act: -0.0001

Data Index: 1064031 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2091. Min Act: -0.0001

Data Index: 1092259 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.1116. Min Act: -0.0001

Data Index: 877860 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2968. Min Act: -0.0001

Data Index: 856846 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.1452. Min Act: -0.0001

Data Index: 981979 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.1537. Min Act: -0.0000

Data Index: 974051 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2609. Min Act: -0.0001

Data Index: 1098553 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.1109. Min Act: -0.0001

Data Index: 706792 (C4 (Web Text))

Max Activating Token Index: 115