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

Dataset: The Pile

Neuron 1610 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2106. Min Range: -1.2106

Max Act: 1.2106. Min Act: -0.0000

Data Index: 1970957 (The Pile)

Max Activating Token Index: 521

Text #1

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9320. Min Act: -0.0000

Data Index: 585179 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9028. Min Act: -0.0000

Data Index: 354029 (The Pile)

Max Activating Token Index: 175

Text #3

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1162848 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8340. Min Act: -0.0000

Data Index: 531800 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.7982. Min Act: -0.0000

Data Index: 730406 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.7344. Min Act: -0.0000

Data Index: 42399 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1642510 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1858282 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.7470. Min Act: -0.0000

Data Index: 588982 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1075912 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1593672 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.7055. Min Act: -0.0000

Data Index: 1726114 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.6804. Min Act: -0.0000

Data Index: 798427 (The Pile)

Max Activating Token Index: 951

Text #14

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.7029. Min Act: -0.0000

Data Index: 7251 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1401343 (The Pile)

Max Activating Token Index: 158

Text #16

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1651736 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1158446 (The Pile)

Max Activating Token Index: 447

Text #18

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.6938. Min Act: -0.0000

Data Index: 538118 (The Pile)

Max Activating Token Index: 389

Text #19

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.6709. Min Act: -0.0000

Data Index: 662187 (The Pile)

Max Activating Token Index: 203