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

Dataset: The Pile

Neuron 384 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1611379 (The Pile)

Max Activating Token Index: 729

Text #1

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8790. Min Act: -0.0000

Data Index: 40769 (The Pile)

Max Activating Token Index: 988

Text #2

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7802. Min Act: -0.0000

Data Index: 746783 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7553. Min Act: -0.0000

Data Index: 335138 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1231646 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6414. Min Act: -0.0000

Data Index: 971168 (The Pile)

Max Activating Token Index: 760

Text #6

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1662551 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1127731 (The Pile)

Max Activating Token Index: 598

Text #8

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1491380 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1001662 (The Pile)

Max Activating Token Index: 878

Text #10

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7563. Min Act: -0.0000

Data Index: 902425 (The Pile)

Max Activating Token Index: 970

Text #11

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7044. Min Act: -0.0000

Data Index: 11205 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6997. Min Act: -0.0000

Data Index: 30982 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1517744 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6748. Min Act: -0.0000

Data Index: 871624 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.9060. Min Act: -0.0000

Data Index: 806870 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6718. Min Act: -0.0000

Data Index: 770083 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1238449 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7340. Min Act: -0.0000

Data Index: 572630 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6664. Min Act: -0.0000

Data Index: 172741 (The Pile)

Max Activating Token Index: 940