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

Dataset: The Pile

Neuron 1640 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: 1.9437. Min Range: -1.9437

Max Act: 1.9437. Min Act: -0.0000

Data Index: 922536 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.8223. Min Act: -0.0000

Data Index: 969723 (The Pile)

Max Activating Token Index: 426

Text #2

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.7887. Min Act: -0.0000

Data Index: 210580 (The Pile)

Max Activating Token Index: 758

Text #3

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.6645. Min Act: -0.0000

Data Index: 760384 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.6054. Min Act: -0.0000

Data Index: 987268 (The Pile)

Max Activating Token Index: 894

Text #5

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.6246. Min Act: -0.0000

Data Index: 593364 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1435791 (The Pile)

Max Activating Token Index: 529

Text #7

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.4945. Min Act: -0.0000

Data Index: 1118957 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.4534. Min Act: -0.0000

Data Index: 986589 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.4422. Min Act: -0.0000

Data Index: 509565 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.3480. Min Act: -0.0000

Data Index: 589296 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.4127. Min Act: -0.0000

Data Index: 113690 (The Pile)

Max Activating Token Index: 810

Text #12

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.4117. Min Act: -0.0000

Data Index: 248131 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.3969. Min Act: -0.0000

Data Index: 436885 (The Pile)

Max Activating Token Index: 473

Text #14

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.3874. Min Act: -0.0000

Data Index: 1039204 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.3157. Min Act: -0.0000

Data Index: 1292996 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.3066. Min Act: -0.0000

Data Index: 1068380 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.2888. Min Act: -0.0000

Data Index: 1628644 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.1911. Min Act: -0.0000

Data Index: 787209 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 1.9437. Min Range: -1.9437

Max Act: 1.3434. Min Act: -0.0000

Data Index: 992489 (The Pile)

Max Activating Token Index: 107