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

Dataset: The Pile

Neuron 3409 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2495. Min Act: 0.0000

Data Index: 659691 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1738042 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1876541 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2220. Min Act: 0.0000

Data Index: 1707107 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2122. Min Act: -0.0000

Data Index: 770849 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1013445 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2222. Min Act: -0.0000

Data Index: 588317 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1973. Min Act: -0.0000

Data Index: 467181 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1374706 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2034. Min Act: -0.0000

Data Index: 865013 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1935. Min Act: -0.0000

Data Index: 243259 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2048. Min Act: -0.0000

Data Index: 508550 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1076820 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1982. Min Act: -0.0000

Data Index: 393976 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1978288 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1973. Min Act: -0.0000

Data Index: 891865 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2117. Min Act: 0.0000

Data Index: 1163331 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1994. Min Act: -0.0000

Data Index: 693268 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1909745 (The Pile)

Max Activating Token Index: 895

Text #19

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1981. Min Act: -0.0000

Data Index: 769307 (The Pile)

Max Activating Token Index: 790