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

Dataset: The Pile

Neuron 3964 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: 1.4458. Min Range: -1.4458

Max Act: 1.4179. Min Act: -0.0000

Data Index: 666165 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.4458. Min Act: -0.0000

Data Index: 285612 (The Pile)

Max Activating Token Index: 911

Text #2

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.3008. Min Act: -0.0000

Data Index: 976698 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.3605. Min Act: -0.0000

Data Index: 1538393 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0781. Min Act: -0.0000

Data Index: 804228 (The Pile)

Max Activating Token Index: 753

Text #5

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.2578. Min Act: -0.0000

Data Index: 1555008 (The Pile)

Max Activating Token Index: 426

Text #6

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.1671. Min Act: -0.0000

Data Index: 911455 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0834. Min Act: -0.0000

Data Index: 1969521 (The Pile)

Max Activating Token Index: 43

Text #8

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1752189 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0438. Min Act: -0.0000

Data Index: 131566 (The Pile)

Max Activating Token Index: 556

Text #10

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0098. Min Act: -0.0000

Data Index: 183165 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9505. Min Act: -0.0000

Data Index: 56649 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1612816 (The Pile)

Max Activating Token Index: 710

Text #13

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1746128 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0175. Min Act: -0.0000

Data Index: 62392 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9451. Min Act: -0.0000

Data Index: 559745 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1605882 (The Pile)

Max Activating Token Index: 437

Text #17

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9333. Min Act: -0.0000

Data Index: 808645 (The Pile)

Max Activating Token Index: 434

Text #18

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.7806. Min Act: -0.0000

Data Index: 77722 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1219467 (The Pile)

Max Activating Token Index: 860