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

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

Neuron 5014 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3188. Min Range: -2.3188

Max Act: 2.3188. Min Act: -0.0000

Data Index: 641667 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.6619. Min Act: -0.0000

Data Index: 58666 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.4620. Min Act: -0.0000

Data Index: 266447 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.4350. Min Act: -0.0000

Data Index: 732970 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.4404. Min Act: -0.0000

Data Index: 1062675 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.2936. Min Act: -0.0000

Data Index: 51941 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.3429. Min Act: -0.0000

Data Index: 24181 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.3275. Min Act: -0.0000

Data Index: 488722 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.3232. Min Act: -0.0000

Data Index: 659696 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.3239. Min Act: -0.0000

Data Index: 424692 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1324168 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.2355. Min Act: -0.0000

Data Index: 543272 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.3090. Min Act: -0.0000

Data Index: 432439 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.2299. Min Act: -0.0000

Data Index: 1062723 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.2101. Min Act: -0.0000

Data Index: 769605 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.3566. Min Act: -0.0000

Data Index: 889267 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.2641. Min Act: -0.0000

Data Index: 965684 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.3443. Min Act: -0.0000

Data Index: 979959 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.1799. Min Act: -0.0000

Data Index: 955811 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 2.3188. Min Range: -2.3188

Max Act: 1.2624. Min Act: -0.0000

Data Index: 100429 (C4 (Web Text))

Max Activating Token Index: 814