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

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

Neuron 2121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3740. Min Act: -0.0000

Data Index: 862948 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3409. Min Act: -0.0000

Data Index: 995699 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3379. Min Act: -0.0001

Data Index: 1350639 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1091257 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2949. Min Act: -0.0000

Data Index: 455948 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3291. Min Act: -0.0001

Data Index: 677075 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2826. Min Act: -0.0000

Data Index: 757885 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1147937 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2789. Min Act: -0.0000

Data Index: 850252 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2866. Min Act: -0.0001

Data Index: 1018588 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1355694 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2613. Min Act: -0.0001

Data Index: 744496 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2597. Min Act: -0.0000

Data Index: 901128 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2410. Min Act: -0.0000

Data Index: 375507 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2438. Min Act: -0.0000

Data Index: 667608 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2406. Min Act: -0.0000

Data Index: 544947 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2405. Min Act: -0.0000

Data Index: 899406 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2401. Min Act: -0.0001

Data Index: 586540 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2464. Min Act: -0.0000

Data Index: 608860 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2746. Min Act: -0.0001

Data Index: 938722 (C4 (Web Text))

Max Activating Token Index: 795