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

Dataset: The Pile

Neuron 55 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.9325. Min Act: -0.0000

Data Index: 633339 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1566120 (The Pile)

Max Activating Token Index: 971

Text #2

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1601953 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.7957. Min Act: -0.0000

Data Index: 163834 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1109873 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.8315. Min Act: -0.0000

Data Index: 967252 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.7614. Min Act: -0.0000

Data Index: 645677 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.8020. Min Act: -0.0000

Data Index: 286028 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1553318 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1227463 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1756133 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.7367. Min Act: -0.0000

Data Index: 266182 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.7727. Min Act: -0.0000

Data Index: 433428 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1751716 (The Pile)

Max Activating Token Index: 539

Text #14

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.7802. Min Act: -0.0000

Data Index: 916464 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1868097 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1509059 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1518760 (The Pile)

Max Activating Token Index: 624

Text #18

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.6810. Min Act: -0.0000

Data Index: 144695 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 0.9325. Min Range: -0.9325

Max Act: 0.7225. Min Act: -0.0000

Data Index: 666475 (The Pile)

Max Activating Token Index: 643