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

Dataset: The Pile

Neuron 2872 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1814236 (The Pile)

Max Activating Token Index: 723

Text #1

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1443328 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1765521 (The Pile)

Max Activating Token Index: 447

Text #3

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2211. Min Act: -0.0000

Data Index: 840201 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1000057 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2047. Min Act: -0.0000

Data Index: 957353 (The Pile)

Max Activating Token Index: 520

Text #6

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1109512 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1026966 (The Pile)

Max Activating Token Index: 879

Text #8

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1093029 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1980519 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2262. Min Act: -0.0000

Data Index: 776634 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1312479 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2080. Min Act: -0.0000

Data Index: 839176 (The Pile)

Max Activating Token Index: 888

Text #13

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2101. Min Act: -0.0000

Data Index: 492264 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.1948. Min Act: -0.0000

Data Index: 480389 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2275. Min Act: -0.0000

Data Index: 774426 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1148569 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1738890 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2174. Min Act: -0.0000

Data Index: 462237 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.1977. Min Act: -0.0000

Data Index: 222754 (The Pile)

Max Activating Token Index: 965