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

Dataset: The Pile

Neuron 210 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.3926. Min Act: -0.0000

Data Index: 1761136 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0487. Min Act: -0.0000

Data Index: 74372 (The Pile)

Max Activating Token Index: 384

Text #2

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8720. Min Act: -0.0000

Data Index: 439266 (The Pile)

Max Activating Token Index: 331

Text #3

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1852375 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8240. Min Act: -0.0000

Data Index: 438578 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1638228 (The Pile)

Max Activating Token Index: 650

Text #6

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1723291 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8084. Min Act: -0.0000

Data Index: 849451 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.7506. Min Act: 0.0000

Data Index: 704985 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1787668 (The Pile)

Max Activating Token Index: 686

Text #10

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1164821 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.6763. Min Act: -0.0000

Data Index: 736191 (The Pile)

Max Activating Token Index: 189

Text #12

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.6981. Min Act: -0.0000

Data Index: 92768 (The Pile)

Max Activating Token Index: 623

Text #13

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1949892 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8568. Min Act: 0.0000

Data Index: 1172678 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.6219. Min Act: -0.0000

Data Index: 837326 (The Pile)

Max Activating Token Index: 822

Text #16

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.7218. Min Act: -0.0000

Data Index: 927119 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1884104 (The Pile)

Max Activating Token Index: 310

Text #18

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1960147 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1025025 (The Pile)

Max Activating Token Index: 399