Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1551 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.5062. Min Act: -0.0000

Data Index: 1259893 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.3297. Min Act: -0.0000

Data Index: 29025 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1457086 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.1087. Min Act: -0.0000

Data Index: 790742 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.1577. Min Act: -0.0000

Data Index: 728089 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1219951 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.0868. Min Act: -0.0000

Data Index: 1311346 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1033075 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.1325. Min Act: -0.0000

Data Index: 21302 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.1989. Min Act: -0.0000

Data Index: 47223 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.0954. Min Act: -0.0000

Data Index: 762812 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1095688 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 1.5062. Min Range: -1.5062

Max Act: 0.9939. Min Act: -0.0000

Data Index: 763105 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.0478. Min Act: -0.0000

Data Index: 666589 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1186644 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.0010. Min Act: -0.0000

Data Index: 68399 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 1.5062. Min Range: -1.5062

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1077132 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 1.5062. Min Range: -1.5062

Max Act: 0.9394. Min Act: -0.0000

Data Index: 966550 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 1.5062. Min Range: -1.5062

Max Act: 0.9934. Min Act: 0.0000

Data Index: 741944 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.5062. Min Range: -1.5062

Max Act: 0.9220. Min Act: -0.0000

Data Index: 679377 (C4 (Web Text))

Max Activating Token Index: 53