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

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

Neuron 1994 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: 2.8420. Min Range: -2.8420

Max Act: 2.7662. Min Act: -0.0000

Data Index: 981149 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.7811. Min Act: -0.0000

Data Index: 1289701 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.8420. Min Act: -0.0000

Data Index: 465646 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.6734. Min Act: -0.0000

Data Index: 195848 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.6079. Min Act: -0.0000

Data Index: 1347192 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.5974. Min Act: -0.0000

Data Index: 163186 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.5743. Min Act: -0.0000

Data Index: 368168 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.7188. Min Act: -0.0000

Data Index: 548647 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.5059. Min Act: -0.0000

Data Index: 211904 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.4984. Min Act: -0.0000

Data Index: 1181010 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.4732. Min Act: -0.0000

Data Index: 1104353 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.5689. Min Act: -0.0000

Data Index: 445629 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.2714. Min Act: -0.0000

Data Index: 1176117 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.3785. Min Act: -0.0000

Data Index: 49204 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.3579. Min Act: -0.0000

Data Index: 1213968 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.3200. Min Act: -0.0000

Data Index: 403080 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.3399. Min Act: -0.0000

Data Index: 1148996 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.3101. Min Act: -0.0000

Data Index: 1082270 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.2410. Min Act: -0.0000

Data Index: 337124 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 2.8420. Min Range: -2.8420

Max Act: 2.0937. Min Act: -0.0000

Data Index: 30876 (C4 (Web Text))

Max Activating Token Index: 361