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

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

Neuron 4601 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0957. Min Act: -0.0000

Data Index: 572451 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1183844 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0371. Min Act: -0.0000

Data Index: 1117540 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0190. Min Act: -0.0000

Data Index: 1349807 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0172. Min Act: -0.0000

Data Index: 573592 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9983. Min Act: -0.0000

Data Index: 795973 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0222. Min Act: -0.0000

Data Index: 638849 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1063486 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9496. Min Act: -0.0000

Data Index: 226761 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9657. Min Act: -0.0000

Data Index: 50562 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9920. Min Act: -0.0000

Data Index: 658152 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9330. Min Act: -0.0000

Data Index: 388264 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9515. Min Act: -0.0000

Data Index: 981989 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9418. Min Act: -0.0000

Data Index: 946956 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9357. Min Act: -0.0000

Data Index: 384122 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1001567 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9544. Min Act: -0.0000

Data Index: 835967 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9293. Min Act: -0.0000

Data Index: 1177110 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9231. Min Act: -0.0000

Data Index: 723620 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9140. Min Act: -0.0000

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 14