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

Dataset: The Pile

Neuron 228 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1296351 (The Pile)

Max Activating Token Index: 634

Text #1

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1533212 (The Pile)

Max Activating Token Index: 139

Text #2

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4807. Min Act: -0.0000

Data Index: 916232 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4252. Min Act: -0.0000

Data Index: 337764 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4256. Min Act: -0.0000

Data Index: 606958 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4483. Min Act: -0.0000

Data Index: 523656 (The Pile)

Max Activating Token Index: 813

Text #6

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4131. Min Act: -0.0000

Data Index: 680198 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1483195 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1390013 (The Pile)

Max Activating Token Index: 632

Text #9

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1329995 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3489. Min Act: -0.0000

Data Index: 387282 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3430. Min Act: -0.0000

Data Index: 182663 (The Pile)

Max Activating Token Index: 965

Text #12

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3581. Min Act: -0.0000

Data Index: 382806 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3467. Min Act: -0.0000

Data Index: 940301 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1813202 (The Pile)

Max Activating Token Index: 122

Text #15

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1058540 (The Pile)

Max Activating Token Index: 31

Text #16

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1128359 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3597. Min Act: -0.0000

Data Index: 918451 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1800932 (The Pile)

Max Activating Token Index: 883

Text #19

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3383. Min Act: -0.0000

Data Index: 814540 (The Pile)

Max Activating Token Index: 1012