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

Dataset: The Pile

Neuron 2678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1580279 (The Pile)

Max Activating Token Index: 826

Text #1

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4237. Min Act: -0.0000

Data Index: 227811 (The Pile)

Max Activating Token Index: 152

Text #2

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1645607 (The Pile)

Max Activating Token Index: 948

Text #3

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1451501 (The Pile)

Max Activating Token Index: 612

Text #4

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3962. Min Act: -0.0000

Data Index: 597002 (The Pile)

Max Activating Token Index: 545

Text #5

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3946. Min Act: -0.0000

Data Index: 66252 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4030. Min Act: -0.0000

Data Index: 818086 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3818. Min Act: -0.0000

Data Index: 705699 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1682432 (The Pile)

Max Activating Token Index: 560

Text #9

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4044. Min Act: -0.0000

Data Index: 917082 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3814. Min Act: -0.0000

Data Index: 241325 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3235. Min Act: -0.0000

Data Index: 503268 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1735311 (The Pile)

Max Activating Token Index: 801

Text #13

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3369. Min Act: -0.0000

Data Index: 802903 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3342. Min Act: -0.0000

Data Index: 545819 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3144. Min Act: -0.0000

Data Index: 424354 (The Pile)

Max Activating Token Index: 289

Text #16

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3014. Min Act: -0.0000

Data Index: 645979 (The Pile)

Max Activating Token Index: 371

Text #17

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3007. Min Act: -0.0000

Data Index: 201191 (The Pile)

Max Activating Token Index: 697

Text #18

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1478810 (The Pile)

Max Activating Token Index: 146

Text #19

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3061. Min Act: -0.0000

Data Index: 684874 (The Pile)

Max Activating Token Index: 83