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

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

Neuron 3969 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.4647. Min Act: -0.0001

Data Index: 1156499 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.3900. Min Act: -0.0001

Data Index: 606333 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.3763. Min Act: -0.0001

Data Index: 189496 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.3625. Min Act: -0.0001

Data Index: 553530 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.3655. Min Act: -0.0001

Data Index: 988385 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.3255. Min Act: -0.0001

Data Index: 1062606 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.3183. Min Act: -0.0001

Data Index: 265888 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2942. Min Act: -0.0001

Data Index: 69867 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.3015. Min Act: -0.0001

Data Index: 1119414 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2991. Min Act: -0.0000

Data Index: 745794 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2868. Min Act: -0.0001

Data Index: 1035653 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2831. Min Act: -0.0001

Data Index: 974521 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1113053 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2836. Min Act: -0.0001

Data Index: 1180757 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2652. Min Act: -0.0000

Data Index: 636137 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2819. Min Act: -0.0001

Data Index: 1059523 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2890. Min Act: -0.0001

Data Index: 688917 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2787. Min Act: -0.0001

Data Index: 657126 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1225917 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.4647. Min Range: -0.4647

Max Act: 0.2763. Min Act: -0.0001

Data Index: 89254 (C4 (Web Text))

Max Activating Token Index: 908