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

Dataset: The Pile

Neuron 4945 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: 1.2143. Min Range: -1.2143

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1391429 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0170. Min Act: -0.0001

Data Index: 1138198 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1471265 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1322090 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1149504 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9544. Min Act: -0.0000

Data Index: 1215275 (The Pile)

Max Activating Token Index: 389

Text #6

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.8632. Min Act: -0.0000

Data Index: 794035 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9866. Min Act: -0.0001

Data Index: 1654457 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9607. Min Act: -0.0000

Data Index: 1252839 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.8721. Min Act: -0.0001

Data Index: 1093719 (The Pile)

Max Activating Token Index: 705

Text #10

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.8392. Min Act: -0.0001

Data Index: 907135 (The Pile)

Max Activating Token Index: 308

Text #11

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1878132 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.6802. Min Act: -0.0000

Data Index: 323510 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.8091. Min Act: -0.0001

Data Index: 1469097 (The Pile)

Max Activating Token Index: 449

Text #14

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.8592. Min Act: -0.0000

Data Index: 53161 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.7610. Min Act: -0.0001

Data Index: 422245 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.8453. Min Act: -0.0000

Data Index: 244510 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.7971. Min Act: -0.0001

Data Index: 1537168 (The Pile)

Max Activating Token Index: 399

Text #18

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.7853. Min Act: -0.0000

Data Index: 182760 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.8540. Min Act: -0.0000

Data Index: 730716 (The Pile)

Max Activating Token Index: 772