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

Dataset: The Pile

Neuron 2147 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.5193. Min Act: -0.0000

Data Index: 1126895 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4248. Min Act: -0.0000

Data Index: 1753779 (The Pile)

Max Activating Token Index: 851

Text #2

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.2465. Min Act: -0.0000

Data Index: 882726 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.8076. Min Act: -0.0000

Data Index: 1268644 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.9380. Min Act: -0.0000

Data Index: 213024 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.8160. Min Act: -0.0000

Data Index: 419743 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.6429. Min Act: -0.0000

Data Index: 1516143 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.6014. Min Act: -0.0000

Data Index: 1724535 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.2462. Min Act: -0.0000

Data Index: 1313410 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.4546. Min Act: -0.0000

Data Index: 1664657 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.3231. Min Act: -0.0000

Data Index: 117794 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.4547. Min Act: -0.0000

Data Index: 674899 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.2605. Min Act: -0.0000

Data Index: 563504 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.5070. Min Act: -0.0000

Data Index: 307809 (The Pile)

Max Activating Token Index: 697

Text #14

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.5579. Min Act: -0.0000

Data Index: 1665190 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.3350. Min Act: -0.0000

Data Index: 1825787 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.3356. Min Act: -0.0000

Data Index: 1683357 (The Pile)

Max Activating Token Index: 77

Text #17

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.4303. Min Act: -0.0000

Data Index: 1635323 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.3302. Min Act: -0.0000

Data Index: 1514869 (The Pile)

Max Activating Token Index: 626

Text #19

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.3216. Min Act: -0.0000

Data Index: 322950 (The Pile)

Max Activating Token Index: 712