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

Dataset: The Pile

Neuron 2635 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: 0.6661. Min Range: -0.6661

Max Act: 0.6661. Min Act: -0.0000

Data Index: 673693 (The Pile)

Max Activating Token Index: 974

Text #1

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1149626 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5798. Min Act: -0.0000

Data Index: 577517 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5214. Min Act: -0.0000

Data Index: 109847 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.6079. Min Act: -0.0000

Data Index: 573297 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1118117 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1260108 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5461. Min Act: -0.0000

Data Index: 473867 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5931. Min Act: -0.0000

Data Index: 125237 (The Pile)

Max Activating Token Index: 983

Text #9

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1725455 (The Pile)

Max Activating Token Index: 921

Text #10

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1974171 (The Pile)

Max Activating Token Index: 872

Text #11

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5272. Min Act: -0.0000

Data Index: 182993 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4761. Min Act: -0.0000

Data Index: 351552 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4926. Min Act: -0.0000

Data Index: 559764 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1658258 (The Pile)

Max Activating Token Index: 782

Text #15

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1412090 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4865. Min Act: -0.0000

Data Index: 401221 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1508644 (The Pile)

Max Activating Token Index: 758

Text #18

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4677. Min Act: -0.0000

Data Index: 843250 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4424. Min Act: -0.0000

Data Index: 606220 (The Pile)

Max Activating Token Index: 142