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

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

Neuron 3116 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.8710. Min Act: -0.0001

Data Index: 609738 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.8108. Min Act: -0.0001

Data Index: 185103 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5657. Min Act: -0.0001

Data Index: 312025 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.6507. Min Act: -0.0001

Data Index: 982410 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.6395. Min Act: -0.0001

Data Index: 43727 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5723. Min Act: -0.0001

Data Index: 1165993 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5544. Min Act: -0.0001

Data Index: 295744 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5678. Min Act: -0.0001

Data Index: 693398 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5574. Min Act: -0.0001

Data Index: 999881 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5309. Min Act: -0.0001

Data Index: 318718 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.4975. Min Act: -0.0001

Data Index: 656542 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5449. Min Act: -0.0001

Data Index: 123138 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5369. Min Act: -0.0001

Data Index: 1307441 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5377. Min Act: -0.0002

Data Index: 1067793 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5186. Min Act: -0.0001

Data Index: 1075901 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.4692. Min Act: -0.0001

Data Index: 440454 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5219. Min Act: -0.0001

Data Index: 457512 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5112. Min Act: -0.0001

Data Index: 376496 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5280. Min Act: -0.0001

Data Index: 320212 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.5132. Min Act: -0.0001

Data Index: 891206 (C4 (Web Text))

Max Activating Token Index: 695