Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1604 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.3575. Min Range: -1.3575

Max Act: 1.3575. Min Act: -0.0000

Data Index: 108564 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 1.3575. Min Range: -1.3575

Max Act: 1.0454. Min Act: -0.0000

Data Index: 887788 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 1.3575. Min Range: -1.3575

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1735186 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9910. Min Act: -0.0001

Data Index: 1464162 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9425. Min Act: -0.0000

Data Index: 283488 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9748. Min Act: -0.0000

Data Index: 121254 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9458. Min Act: -0.0000

Data Index: 671051 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9012. Min Act: -0.0000

Data Index: 111016 (The Pile)

Max Activating Token Index: 297

Text #8

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8995. Min Act: -0.0000

Data Index: 357581 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9040. Min Act: -0.0000

Data Index: 977494 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9285. Min Act: -0.0000

Data Index: 225313 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1438864 (The Pile)

Max Activating Token Index: 507

Text #12

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9099. Min Act: -0.0000

Data Index: 293699 (The Pile)

Max Activating Token Index: 294

Text #13

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8521. Min Act: -0.0000

Data Index: 293848 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8547. Min Act: -0.0000

Data Index: 977766 (The Pile)

Max Activating Token Index: 853

Text #15

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9270. Min Act: -0.0001

Data Index: 340109 (The Pile)

Max Activating Token Index: 955

Text #16

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1707064 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8329. Min Act: -0.0000

Data Index: 504387 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1035705 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1941184 (The Pile)

Max Activating Token Index: 320