Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1850 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1737. Min Range: -1.1737

Max Act: 1.1737. Min Act: -0.0001

Data Index: 1243251 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 1.1737. Min Range: -1.1737

Max Act: 0.9991. Min Act: -0.0001

Data Index: 525014 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.1737. Min Range: -1.1737

Max Act: 1.0717. Min Act: -0.0001

Data Index: 1348774 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.1737. Min Range: -1.1737

Max Act: 1.1714. Min Act: -0.0001

Data Index: 316932 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 1.1737. Min Range: -1.1737

Max Act: 1.0928. Min Act: -0.0001

Data Index: 1277647 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 1.1737. Min Range: -1.1737

Max Act: 1.0947. Min Act: -0.0001

Data Index: 936261 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.1737. Min Range: -1.1737

Max Act: 1.0512. Min Act: -0.0001

Data Index: 706732 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 1.1737. Min Range: -1.1737

Max Act: 1.0506. Min Act: -0.0001

Data Index: 1007745 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 1.1737. Min Range: -1.1737

Max Act: 1.0461. Min Act: -0.0001

Data Index: 1007789 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 1.1737. Min Range: -1.1737

Max Act: 0.9568. Min Act: -0.0001

Data Index: 1094174 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 1.1737. Min Range: -1.1737

Max Act: 0.9869. Min Act: -0.0000

Data Index: 457211 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 1.1737. Min Range: -1.1737

Max Act: 1.0410. Min Act: -0.0001

Data Index: 40494 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 1.1737. Min Range: -1.1737

Max Act: 0.9049. Min Act: -0.0001

Data Index: 817015 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 1.1737. Min Range: -1.1737

Max Act: 0.9397. Min Act: -0.0001

Data Index: 531902 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.1737. Min Range: -1.1737

Max Act: 0.7099. Min Act: -0.0001

Data Index: 354710 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.1737. Min Range: -1.1737

Max Act: 0.9700. Min Act: -0.0001

Data Index: 827896 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.1737. Min Range: -1.1737

Max Act: 0.9436. Min Act: -0.0001

Data Index: 905475 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 1.1737. Min Range: -1.1737

Max Act: 0.6963. Min Act: -0.0001

Data Index: 541041 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 1.1737. Min Range: -1.1737

Max Act: 0.8682. Min Act: -0.0001

Data Index: 462210 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.1737. Min Range: -1.1737

Max Act: 0.8441. Min Act: -0.0001

Data Index: 490515 (C4 (Web Text))

Max Activating Token Index: 627