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

Dataset: The Pile

Neuron 1975 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: 0.9064. Min Range: -0.9064

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1358154 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1206182 (The Pile)

Max Activating Token Index: 507

Text #2

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7771. Min Act: -0.0000

Data Index: 402568 (The Pile)

Max Activating Token Index: 338

Text #3

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7418. Min Act: -0.0000

Data Index: 294490 (The Pile)

Max Activating Token Index: 514

Text #4

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1595562 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1311046 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1051824 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1306627 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1093725 (The Pile)

Max Activating Token Index: 662

Text #9

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7267. Min Act: -0.0000

Data Index: 632198 (The Pile)

Max Activating Token Index: 387

Text #10

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7229. Min Act: -0.0000

Data Index: 384993 (The Pile)

Max Activating Token Index: 889

Text #11

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1130686 (The Pile)

Max Activating Token Index: 432

Text #12

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1072186 (The Pile)

Max Activating Token Index: 482

Text #13

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6430. Min Act: -0.0000

Data Index: 365291 (The Pile)

Max Activating Token Index: 858

Text #14

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6587. Min Act: -0.0000

Data Index: 454632 (The Pile)

Max Activating Token Index: 373

Text #15

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6602. Min Act: -0.0000

Data Index: 597085 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1990098 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1238345 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1939847 (The Pile)

Max Activating Token Index: 1013

Text #19

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6926. Min Act: -0.0000

Data Index: 122153 (The Pile)

Max Activating Token Index: 20