Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 604 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2828. Min Act: -0.0002

Data Index: 112878 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2716. Min Act: -0.0001

Data Index: 67128 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2430. Min Act: -0.0002

Data Index: 1344386 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2172. Min Act: -0.0002

Data Index: 876354 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2159. Min Act: -0.0002

Data Index: 948434 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2042. Min Act: -0.0001

Data Index: 1312515 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2081. Min Act: -0.0002

Data Index: 493778 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1939. Min Act: -0.0001

Data Index: 510126 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2080. Min Act: -0.0002

Data Index: 634026 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2136. Min Act: -0.0002

Data Index: 1291942 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2063. Min Act: -0.0002

Data Index: 1294305 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2069. Min Act: -0.0002

Data Index: 1175051 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1983. Min Act: -0.0002

Data Index: 353956 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2130. Min Act: -0.0002

Data Index: 806624 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2066. Min Act: -0.0002

Data Index: 903246 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2145. Min Act: -0.0001

Data Index: 712451 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2113. Min Act: -0.0002

Data Index: 1051714 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2104. Min Act: -0.0002

Data Index: 1050195 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1893. Min Act: -0.0002

Data Index: 593651 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1883. Min Act: -0.0002

Data Index: 768967 (C4 (Web Text))

Max Activating Token Index: 630