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

Dataset: The Pile

Neuron 2034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0671. Min Act: -0.0000

Data Index: 1196652 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1335011 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9982. Min Act: -0.0000

Data Index: 252622 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0768. Min Act: -0.0000

Data Index: 256523 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0474. Min Act: -0.0000

Data Index: 459900 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0376. Min Act: -0.0000

Data Index: 828950 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9999. Min Act: -0.0000

Data Index: 1831422 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0649. Min Act: -0.0000

Data Index: 971140 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1587203 (The Pile)

Max Activating Token Index: 712

Text #9

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1082805 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1477918 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9409. Min Act: -0.0000

Data Index: 891161 (The Pile)

Max Activating Token Index: 824

Text #12

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9571. Min Act: -0.0000

Data Index: 719774 (The Pile)

Max Activating Token Index: 931

Text #13

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1887951 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0391. Min Act: -0.0000

Data Index: 979347 (The Pile)

Max Activating Token Index: 883

Text #15

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9506. Min Act: -0.0000

Data Index: 848260 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1310117 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9094. Min Act: -0.0000

Data Index: 313553 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9049. Min Act: -0.0000

Data Index: 459325 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1526490 (The Pile)

Max Activating Token Index: 916