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

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

Neuron 5159 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.8082. Min Act: -0.0000

Data Index: 1301340 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.4213. Min Act: -0.0000

Data Index: 949328 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.5067. Min Act: -0.0000

Data Index: 1104533 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.4828. Min Act: -0.0000

Data Index: 45485 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.1927. Min Act: -0.0000

Data Index: 1157454 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.0944. Min Act: -0.0000

Data Index: 658033 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.1744. Min Act: -0.0000

Data Index: 662941 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.1742. Min Act: -0.0000

Data Index: 1166502 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.1926. Min Act: -0.0000

Data Index: 756783 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.2001. Min Act: -0.0000

Data Index: 1130150 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.1638. Min Act: -0.0000

Data Index: 354014 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.1512. Min Act: -0.0000

Data Index: 948616 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.2542. Min Act: -0.0000

Data Index: 1149622 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.0293. Min Act: -0.0000

Data Index: 402240 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.2261. Min Act: -0.0000

Data Index: 878773 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.0948. Min Act: -0.0000

Data Index: 1181773 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.0838. Min Act: -0.0000

Data Index: 108151 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.0870. Min Act: -0.0000

Data Index: 540890 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 2.8082. Min Range: -2.8082

Max Act: 1.9363. Min Act: -0.0000

Data Index: 98807 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 2.8082. Min Range: -2.8082

Max Act: 2.0358. Min Act: -0.0000

Data Index: 31034 (C4 (Web Text))

Max Activating Token Index: 971