Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 502 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.5860. Min Act: -0.0000

Data Index: 661781 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1339648 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1353788 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4653. Min Act: -0.0001

Data Index: 134386 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4220. Min Act: -0.0001

Data Index: 773262 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4292. Min Act: -0.0000

Data Index: 559785 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4513. Min Act: -0.0001

Data Index: 66754 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4194. Min Act: -0.0001

Data Index: 1234094 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4145. Min Act: -0.0001

Data Index: 1007825 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3905. Min Act: -0.0001

Data Index: 292523 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4169. Min Act: -0.0000

Data Index: 419005 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4153. Min Act: -0.0001

Data Index: 1022422 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4005. Min Act: -0.0001

Data Index: 427893 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3816. Min Act: -0.0001

Data Index: 1166622 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3871. Min Act: -0.0001

Data Index: 579959 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4060. Min Act: -0.0000

Data Index: 612723 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3675. Min Act: -0.0000

Data Index: 346324 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3678. Min Act: -0.0001

Data Index: 801065 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3394. Min Act: -0.0001

Data Index: 368816 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3508. Min Act: -0.0001

Data Index: 450261 (C4 (Web Text))

Max Activating Token Index: 909