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

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

Neuron 3748 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1292419 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4599. Min Act: -0.0000

Data Index: 499504 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3970. Min Act: -0.0000

Data Index: 321365 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4419. Min Act: -0.0000

Data Index: 460188 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4101. Min Act: -0.0000

Data Index: 346347 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3796. Min Act: -0.0000

Data Index: 656071 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3758. Min Act: -0.0000

Data Index: 91136 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1408718 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3645. Min Act: -0.0000

Data Index: 191120 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3836. Min Act: -0.0000

Data Index: 683421 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1342618 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3798. Min Act: -0.0000

Data Index: 921345 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1289190 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3533. Min Act: -0.0000

Data Index: 762945 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3322. Min Act: -0.0000

Data Index: 665928 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3625. Min Act: -0.0000

Data Index: 132386 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3489. Min Act: -0.0000

Data Index: 673830 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3589. Min Act: -0.0000

Data Index: 368844 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1106184 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3950. Min Act: -0.0000

Data Index: 444053 (C4 (Web Text))

Max Activating Token Index: 857