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

Dataset: The Pile

Neuron 83 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0183. Min Range: -1.0183

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1264860 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.9144. Min Act: -0.0000

Data Index: 31228 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8728. Min Act: -0.0000

Data Index: 327916 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1695867 (The Pile)

Max Activating Token Index: 901

Text #4

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8290. Min Act: -0.0000

Data Index: 110474 (The Pile)

Max Activating Token Index: 981

Text #5

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1796444 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1799231 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8265. Min Act: -0.0000

Data Index: 303383 (The Pile)

Max Activating Token Index: 642

Text #8

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1581583 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1825860 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1594959 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1493267 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7367. Min Act: -0.0000

Data Index: 519082 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1726652 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7202. Min Act: -0.0000

Data Index: 179324 (The Pile)

Max Activating Token Index: 243

Text #15

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1593881 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6960. Min Act: -0.0000

Data Index: 449157 (The Pile)

Max Activating Token Index: 145

Text #17

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6705. Min Act: -0.0000

Data Index: 688248 (The Pile)

Max Activating Token Index: 42

Text #18

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1565454 (The Pile)

Max Activating Token Index: 752

Text #19

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1445983 (The Pile)

Max Activating Token Index: 148