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

Dataset: The Pile

Neuron 942 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: 1.3489. Min Range: -1.3489

Max Act: 1.3489. Min Act: -0.0000

Data Index: 150539 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1187. Min Act: -0.0000

Data Index: 826644 (The Pile)

Max Activating Token Index: 676

Text #2

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1183540 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0665. Min Act: -0.0000

Data Index: 439763 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1709312 (The Pile)

Max Activating Token Index: 506

Text #5

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0273. Min Act: -0.0000

Data Index: 538867 (The Pile)

Max Activating Token Index: 741

Text #6

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0120. Min Act: -0.0000

Data Index: 877598 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1982346 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1409622 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9650. Min Act: -0.0000

Data Index: 969908 (The Pile)

Max Activating Token Index: 240

Text #10

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9319. Min Act: -0.0000

Data Index: 81821 (The Pile)

Max Activating Token Index: 347

Text #11

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0076. Min Act: -0.0000

Data Index: 769819 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1263612 (The Pile)

Max Activating Token Index: 116

Text #13

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1493570 (The Pile)

Max Activating Token Index: 303

Text #14

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9650. Min Act: -0.0000

Data Index: 977495 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1272255 (The Pile)

Max Activating Token Index: 999

Text #16

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1619971 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9381. Min Act: -0.0000

Data Index: 450965 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9604. Min Act: -0.0000

Data Index: 951399 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9220. Min Act: -0.0000

Data Index: 925181 (The Pile)

Max Activating Token Index: 239