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

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

Neuron 4718 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1365. Min Act: -0.0000

Data Index: 529237 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1224. Min Act: -0.0000

Data Index: 295783 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1000. Min Act: -0.0000

Data Index: 466105 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1068. Min Act: -0.0000

Data Index: 674311 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0944. Min Act: -0.0000

Data Index: 708597 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0996. Min Act: -0.0000

Data Index: 354295 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1222440 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1345073 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0967. Min Act: -0.0000

Data Index: 499800 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1266071 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0963. Min Act: -0.0000

Data Index: 190237 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0921. Min Act: -0.0000

Data Index: 666416 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0882. Min Act: -0.0000

Data Index: 819911 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0866. Min Act: -0.0000

Data Index: 400644 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1168966 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0954. Min Act: -0.0000

Data Index: 631018 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0851. Min Act: -0.0000

Data Index: 834292 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0851. Min Act: -0.0000

Data Index: 829990 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0877. Min Act: -0.0000

Data Index: 266803 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0871. Min Act: -0.0000

Data Index: 276640 (C4 (Web Text))

Max Activating Token Index: 9