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

Dataset: The Pile

Neuron 616 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.5080. Min Act: -0.0000

Data Index: 1539082 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.7297. Min Act: -0.0000

Data Index: 1070536 (The Pile)

Max Activating Token Index: 744

Text #2

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.4421. Min Act: -0.0000

Data Index: 333378 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.4573. Min Act: -0.0000

Data Index: 920913 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.7273. Min Act: -0.0000

Data Index: 765851 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.3204. Min Act: -0.0000

Data Index: 1216547 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.3780. Min Act: -0.0000

Data Index: 98284 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.4033. Min Act: -0.0000

Data Index: 896353 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1937360 (The Pile)

Max Activating Token Index: 673

Text #9

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.5255. Min Act: -0.0000

Data Index: 484453 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1231262 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.3305. Min Act: -0.0000

Data Index: 400299 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.3034. Min Act: -0.0000

Data Index: 990090 (The Pile)

Max Activating Token Index: 298

Text #13

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.5050. Min Act: -0.0000

Data Index: 734174 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.5450. Min Act: -0.0000

Data Index: 1448607 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.3797. Min Act: -0.0000

Data Index: 731771 (The Pile)

Max Activating Token Index: 792

Text #16

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.3074. Min Act: -0.0000

Data Index: 189120 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.2685. Min Act: -0.0000

Data Index: 805081 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1309756 (The Pile)

Max Activating Token Index: 788

Text #19

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1435046 (The Pile)

Max Activating Token Index: 766