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

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

Neuron 5314 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: 0.6585. Min Range: -0.6585

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1117512 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.6384. Min Act: -0.0000

Data Index: 384813 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.6390. Min Act: -0.0000

Data Index: 592619 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.6585. Min Act: -0.0000

Data Index: 278192 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5808. Min Act: -0.0000

Data Index: 684930 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.6023. Min Act: -0.0000

Data Index: 237096 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5182. Min Act: -0.0000

Data Index: 949581 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1055506 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5105. Min Act: -0.0000

Data Index: 920738 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5040. Min Act: -0.0000

Data Index: 431258 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.4967. Min Act: -0.0000

Data Index: 735024 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5010. Min Act: -0.0000

Data Index: 40443 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.4161. Min Act: -0.0000

Data Index: 917519 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5042. Min Act: -0.0000

Data Index: 96626 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.4727. Min Act: -0.0000

Data Index: 18387 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.4673. Min Act: -0.0000

Data Index: 808364 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.4541. Min Act: -0.0000

Data Index: 247437 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.4136. Min Act: -0.0000

Data Index: 147321 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.4389. Min Act: -0.0000

Data Index: 677004 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.4162. Min Act: -0.0000

Data Index: 569175 (C4 (Web Text))

Max Activating Token Index: 333