Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 170 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.4469. Min Act: -0.0000

Data Index: 25085 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.4053. Min Act: -0.0000

Data Index: 533001 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3783. Min Act: -0.0000

Data Index: 790663 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3774. Min Act: -0.0000

Data Index: 411723 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3790. Min Act: -0.0000

Data Index: 402119 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.4021. Min Act: -0.0000

Data Index: 252125 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3606. Min Act: -0.0000

Data Index: 434187 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3640. Min Act: -0.0000

Data Index: 968305 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3641. Min Act: -0.0000

Data Index: 334736 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3716. Min Act: -0.0000

Data Index: 170295 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3569. Min Act: -0.0000

Data Index: 135119 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3321. Min Act: -0.0000

Data Index: 930390 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3502. Min Act: -0.0000

Data Index: 836864 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1052004 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3282. Min Act: -0.0000

Data Index: 453448 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3523. Min Act: -0.0000

Data Index: 706435 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3780. Min Act: -0.0000

Data Index: 85454 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3506. Min Act: -0.0000

Data Index: 17366 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3482. Min Act: -0.0000

Data Index: 292953 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1140940 (C4 (Web Text))

Max Activating Token Index: 972