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

Dataset: The Pile

Neuron 4134 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: 0.9826. Min Range: -0.9826

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1328406 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.9826. Min Act: -0.0000

Data Index: 581528 (The Pile)

Max Activating Token Index: 530

Text #2

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1261261 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1763784 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7514. Min Act: -0.0000

Data Index: 895854 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7142. Min Act: -0.0000

Data Index: 963223 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1955987 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6970. Min Act: -0.0000

Data Index: 475624 (The Pile)

Max Activating Token Index: 263

Text #8

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1468286 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6481. Min Act: -0.0000

Data Index: 184995 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6717. Min Act: -0.0000

Data Index: 954277 (The Pile)

Max Activating Token Index: 800

Text #11

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6680. Min Act: -0.0000

Data Index: 269447 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1956262 (The Pile)

Max Activating Token Index: 217

Text #13

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6359. Min Act: -0.0000

Data Index: 123096 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1428910 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6050. Min Act: -0.0000

Data Index: 142398 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6229. Min Act: -0.0000

Data Index: 762857 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6166. Min Act: -0.0000

Data Index: 119896 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6163. Min Act: -0.0000

Data Index: 976044 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6150. Min Act: -0.0000

Data Index: 672540 (The Pile)

Max Activating Token Index: 166