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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2560 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9904. Min Act: -0.0002

Data Index: 1314644 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9294. Min Act: -0.0001

Data Index: 467959 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9493. Min Act: -0.0001

Data Index: 1178298 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9630. Min Act: -0.0002

Data Index: 1123171 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9030. Min Act: -0.0002

Data Index: 261743 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9282. Min Act: -0.0001

Data Index: 224133 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9327. Min Act: -0.0002

Data Index: 590078 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8878. Min Act: -0.0002

Data Index: 484397 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9149. Min Act: -0.0002

Data Index: 326240 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9097. Min Act: -0.0001

Data Index: 906189 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8988. Min Act: -0.0002

Data Index: 810355 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8957. Min Act: -0.0002

Data Index: 354066 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8424. Min Act: -0.0002

Data Index: 302500 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8645. Min Act: -0.0001

Data Index: 1018726 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8892. Min Act: -0.0002

Data Index: 30328 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8468. Min Act: -0.0002

Data Index: 388137 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8538. Min Act: -0.0002

Data Index: 660745 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8505. Min Act: -0.0001

Data Index: 385007 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8244. Min Act: -0.0002

Data Index: 410539 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8251. Min Act: -0.0001

Data Index: 829432 (C4 (Web Text))

Max Activating Token Index: 886