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

Dataset: The Pile

Neuron 4694 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1492. Min Act: -0.0000

Data Index: 16468 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1013358 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1242228 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1331080 (The Pile)

Max Activating Token Index: 411

Text #4

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1018. Min Act: -0.0000

Data Index: 449337 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.0956. Min Act: -0.0000

Data Index: 384676 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1001. Min Act: -0.0000

Data Index: 804092 (The Pile)

Max Activating Token Index: 400

Text #7

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.0844. Min Act: -0.0000

Data Index: 6432 (The Pile)

Max Activating Token Index: 885

Text #8

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.0922. Min Act: -0.0000

Data Index: 594547 (The Pile)

Max Activating Token Index: 666

Text #9

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1388053 (The Pile)

Max Activating Token Index: 1000

Text #10

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1083. Min Act: -0.0000

Data Index: 192625 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1006. Min Act: -0.0000

Data Index: 982041 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1878662 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.0937. Min Act: -0.0000

Data Index: 370930 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1295077 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.0994. Min Act: -0.0000

Data Index: 961393 (The Pile)

Max Activating Token Index: 327

Text #16

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1001. Min Act: -0.0000

Data Index: 490111 (The Pile)

Max Activating Token Index: 590

Text #17

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1202076 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1018. Min Act: -0.0000

Data Index: 969322 (The Pile)

Max Activating Token Index: 603

Text #19

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1442050 (The Pile)

Max Activating Token Index: 238