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

Dataset: The Pile

Neuron 1295 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: 0.6661. Min Range: -0.6661

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1172958 (The Pile)

Max Activating Token Index: 924

Text #1

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.6638. Min Act: -0.0000

Data Index: 689928 (The Pile)

Max Activating Token Index: 501

Text #2

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1593291 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5751. Min Act: -0.0000

Data Index: 118357 (The Pile)

Max Activating Token Index: 934

Text #4

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1574074 (The Pile)

Max Activating Token Index: 871

Text #5

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1789422 (The Pile)

Max Activating Token Index: 392

Text #6

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1030253 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1042567 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5275. Min Act: -0.0000

Data Index: 129625 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1722 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5786. Min Act: -0.0000

Data Index: 962986 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5189. Min Act: -0.0000

Data Index: 829292 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1066676 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1181617 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4997. Min Act: -0.0000

Data Index: 288856 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1844023 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5114. Min Act: -0.0000

Data Index: 650195 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5033. Min Act: -0.0000

Data Index: 535950 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1117110 (The Pile)

Max Activating Token Index: 270

Text #19

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1843321 (The Pile)

Max Activating Token Index: 852