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

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

Neuron 1058 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.2760. Min Act: -0.0000

Data Index: 374292 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0532. Min Act: -0.0001

Data Index: 728126 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.5695. Min Act: -0.0001

Data Index: 184909 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.5719. Min Act: -0.0001

Data Index: 1044034 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.4186. Min Act: -0.0000

Data Index: 908486 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.2520. Min Act: -0.0001

Data Index: 298678 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.2811. Min Act: -0.0001

Data Index: 1013397 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.2573. Min Act: -0.0000

Data Index: 70965 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.3615. Min Act: -0.0001

Data Index: 1132008 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.2169. Min Act: -0.0000

Data Index: 1096404 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.2173. Min Act: -0.0001

Data Index: 480425 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.2247. Min Act: -0.0001

Data Index: 163498 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.2192. Min Act: -0.0001

Data Index: 784487 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.1991. Min Act: -0.0001

Data Index: 1258330 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.2909. Min Act: -0.0001

Data Index: 494838 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.1432. Min Act: -0.0000

Data Index: 1048075 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.1447. Min Act: -0.0001

Data Index: 657080 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.0126. Min Act: -0.0000

Data Index: 855434 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 3.2760. Min Range: -3.2760

Max Act: 2.0092. Min Act: -0.0000

Data Index: 939210 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 3.2760. Min Range: -3.2760

Max Act: 1.9843. Min Act: -0.0000

Data Index: 747688 (C4 (Web Text))

Max Activating Token Index: 45