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

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

Neuron 3200 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0712. Min Act: -0.0001

Data Index: 735386 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0734. Min Act: -0.0001

Data Index: 663846 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0614. Min Act: -0.0001

Data Index: 176842 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1024259 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0640. Min Act: -0.0001

Data Index: 418074 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0590. Min Act: -0.0001

Data Index: 860357 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0499. Min Act: -0.0001

Data Index: 538480 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0526. Min Act: -0.0001

Data Index: 795832 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0518. Min Act: -0.0001

Data Index: 140692 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0575. Min Act: -0.0001

Data Index: 46708 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0519. Min Act: -0.0001

Data Index: 175607 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0503. Min Act: -0.0001

Data Index: 529163 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1110728 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0456. Min Act: -0.0001

Data Index: 287958 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0476. Min Act: -0.0001

Data Index: 967750 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0447. Min Act: -0.0001

Data Index: 624030 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0428. Min Act: -0.0001

Data Index: 239819 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1296844 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0516. Min Act: -0.0001

Data Index: 500467 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1132269 (C4 (Web Text))

Max Activating Token Index: 10