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

Dataset: The Pile

Neuron 3017 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.4061. Min Act: -0.0000

Data Index: 685974 (The Pile)

Max Activating Token Index: 908

Text #1

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.3338. Min Act: 0.0000

Data Index: 462450 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1183166 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2977. Min Act: -0.0000

Data Index: 27861 (The Pile)

Max Activating Token Index: 559

Text #4

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2980. Min Act: 0.0000

Data Index: 1483370 (The Pile)

Max Activating Token Index: 136

Text #5

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2925. Min Act: 0.0000

Data Index: 459399 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.4163. Min Act: -0.0000

Data Index: 611600 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1877. Min Act: -0.0000

Data Index: 421060 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2624. Min Act: 0.0000

Data Index: 950267 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2215. Min Act: 0.0000

Data Index: 1918930 (The Pile)

Max Activating Token Index: 161

Text #10

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1855. Min Act: -0.0000

Data Index: 331032 (The Pile)

Max Activating Token Index: 178

Text #11

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2060. Min Act: -0.0000

Data Index: 378071 (The Pile)

Max Activating Token Index: 56

Text #12

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2048. Min Act: 0.0000

Data Index: 593734 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2041. Min Act: 0.0000

Data Index: 1910651 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2013. Min Act: -0.0000

Data Index: 1132642 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1208. Min Act: 0.0000

Data Index: 524543 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1968. Min Act: 0.0000

Data Index: 162510 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1713. Min Act: 0.0000

Data Index: 621063 (The Pile)

Max Activating Token Index: 599

Text #18

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1725. Min Act: -0.0000

Data Index: 931452 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1767321 (The Pile)

Max Activating Token Index: 252