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

Dataset: The Pile

Neuron 4422 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1811091 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1230040 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1201724 (The Pile)

Max Activating Token Index: 693

Text #3

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1746746 (The Pile)

Max Activating Token Index: 698

Text #4

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1333212 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1049637 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2169. Min Act: -0.0000

Data Index: 141027 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1191442 (The Pile)

Max Activating Token Index: 557

Text #8

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1273723 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1813737 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2036. Min Act: -0.0000

Data Index: 197555 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.1972. Min Act: -0.0000

Data Index: 900134 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1478119 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1129159 (The Pile)

Max Activating Token Index: 29

Text #14

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1233560 (The Pile)

Max Activating Token Index: 913

Text #15

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1771303 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2013. Min Act: -0.0000

Data Index: 229510 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1427677 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2165. Min Act: -0.0000

Data Index: 918413 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2026. Min Act: -0.0000

Data Index: 891448 (The Pile)

Max Activating Token Index: 1005