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

Dataset: The Pile

Neuron 4702 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: 7.2799. Min Range: -7.2799

Max Act: 7.2799. Min Act: -0.0000

Data Index: 486438 (The Pile)

Max Activating Token Index: 390

Text #1

Max Range: 7.2799. Min Range: -7.2799

Max Act: 7.2493. Min Act: -0.0000

Data Index: 1083134 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.9498. Min Act: -0.0000

Data Index: 1872949 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.9282. Min Act: -0.0000

Data Index: 1272041 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 7.2799. Min Range: -7.2799

Max Act: 7.1191. Min Act: -0.0000

Data Index: 909273 (The Pile)

Max Activating Token Index: 357

Text #5

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.8139. Min Act: -0.0000

Data Index: 1780019 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.6070. Min Act: -0.0000

Data Index: 1087932 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.7763. Min Act: -0.0000

Data Index: 1629470 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.4862. Min Act: -0.0000

Data Index: 698924 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.4802. Min Act: -0.0000

Data Index: 1030364 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.2215. Min Act: -0.0000

Data Index: 1541875 (The Pile)

Max Activating Token Index: 662

Text #11

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.4121. Min Act: -0.0000

Data Index: 400867 (The Pile)

Max Activating Token Index: 322

Text #12

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.3534. Min Act: -0.0000

Data Index: 399624 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.2097. Min Act: -0.0000

Data Index: 882950 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.8568. Min Act: -0.0000

Data Index: 1832804 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.6092. Min Act: -0.0000

Data Index: 1142207 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.4031. Min Act: -0.0000

Data Index: 1236892 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 7.2799. Min Range: -7.2799

Max Act: 5.9561. Min Act: -0.0000

Data Index: 322997 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 7.2799. Min Range: -7.2799

Max Act: 5.9551. Min Act: -0.0000

Data Index: 724505 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 7.2799. Min Range: -7.2799

Max Act: 6.0362. Min Act: -0.0000

Data Index: 665867 (The Pile)

Max Activating Token Index: 568