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

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

Neuron 1987 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1173267 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2548. Min Act: -0.0001

Data Index: 618722 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2275. Min Act: -0.0001

Data Index: 741106 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2219. Min Act: -0.0001

Data Index: 1085046 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2161. Min Act: -0.0001

Data Index: 1326402 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2022. Min Act: -0.0001

Data Index: 1021205 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2021. Min Act: -0.0001

Data Index: 840184 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2042. Min Act: -0.0001

Data Index: 22593 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2023. Min Act: -0.0001

Data Index: 994934 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1231446 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1972. Min Act: -0.0001

Data Index: 163785 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1969. Min Act: -0.0001

Data Index: 585704 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1970. Min Act: -0.0001

Data Index: 776854 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1896. Min Act: -0.0001

Data Index: 958593 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1924. Min Act: -0.0001

Data Index: 1338867 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1834. Min Act: -0.0001

Data Index: 1289643 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1165391 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1718. Min Act: -0.0000

Data Index: 143763 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1761. Min Act: -0.0000

Data Index: 948154 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1813. Min Act: -0.0000

Data Index: 252024 (C4 (Web Text))

Max Activating Token Index: 682