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

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

Neuron 2438 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: 1.7295. Min Range: -1.7295

Max Act: 1.6706. Min Act: -0.0000

Data Index: 55636 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.6544. Min Act: -0.0001

Data Index: 253961 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.7295. Min Act: -0.0001

Data Index: 353670 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.3548. Min Act: -0.0001

Data Index: 368847 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.3035. Min Act: -0.0000

Data Index: 1000061 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.4667. Min Act: -0.0001

Data Index: 1114740 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.4521. Min Act: -0.0000

Data Index: 52857 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.4113. Min Act: -0.0001

Data Index: 1354751 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.2752. Min Act: -0.0000

Data Index: 1051294 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.3382. Min Act: -0.0001

Data Index: 1322020 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.5410. Min Act: -0.0001

Data Index: 1093576 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.4533. Min Act: -0.0000

Data Index: 955005 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.3655. Min Act: -0.0000

Data Index: 449818 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.2648. Min Act: -0.0000

Data Index: 359192 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.2264. Min Act: -0.0000

Data Index: 892219 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.2255. Min Act: -0.0000

Data Index: 911582 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.2317. Min Act: -0.0000

Data Index: 1007733 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.2629. Min Act: -0.0000

Data Index: 655252 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.2470. Min Act: -0.0000

Data Index: 1184509 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 1.7295. Min Range: -1.7295

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1084152 (C4 (Web Text))

Max Activating Token Index: 451