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

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

Neuron 2666 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: 2.9150. Min Range: -2.9150

Max Act: 2.9150. Min Act: -0.0000

Data Index: 1062946 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.5840. Min Act: -0.0001

Data Index: 260222 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.3035. Min Act: -0.0000

Data Index: 433030 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.3973. Min Act: -0.0000

Data Index: 153333 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.2856. Min Act: -0.0001

Data Index: 422806 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.1280. Min Act: -0.0001

Data Index: 93076 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.3070. Min Act: -0.0000

Data Index: 1196857 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.3309. Min Act: -0.0000

Data Index: 513830 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 2.9150. Min Range: -2.9150

Max Act: 1.9946. Min Act: -0.0000

Data Index: 327135 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.1540. Min Act: -0.0000

Data Index: 1302289 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.1378. Min Act: -0.0001

Data Index: 903935 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.1025. Min Act: -0.0000

Data Index: 1260994 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.0025. Min Act: -0.0000

Data Index: 1034641 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.0607. Min Act: -0.0000

Data Index: 655665 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.3281. Min Act: -0.0001

Data Index: 944627 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.1534. Min Act: -0.0001

Data Index: 949968 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 2.9150. Min Range: -2.9150

Max Act: 1.9637. Min Act: -0.0000

Data Index: 961831 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.0560. Min Act: -0.0001

Data Index: 896200 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.1649. Min Act: -0.0001

Data Index: 1065518 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 2.9150. Min Range: -2.9150

Max Act: 2.0410. Min Act: -0.0000

Data Index: 964438 (C4 (Web Text))

Max Activating Token Index: 161