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

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

Neuron 2783 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: 1.1288. Min Range: -1.1288

Max Act: 1.1288. Min Act: -0.0000

Data Index: 669865 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.1287. Min Act: 0.0000

Data Index: 798273 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9539. Min Act: -0.0000

Data Index: 295489 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.0860. Min Act: -0.0000

Data Index: 375690 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1060782 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9938. Min Act: 0.0000

Data Index: 1267020 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.0570. Min Act: -0.0000

Data Index: 170589 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.0342. Min Act: -0.0000

Data Index: 596063 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9936. Min Act: -0.0000

Data Index: 341563 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9599. Min Act: -0.0000

Data Index: 731956 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9471. Min Act: -0.0000

Data Index: 306425 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9371. Min Act: -0.0000

Data Index: 396394 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8610. Min Act: 0.0000

Data Index: 711438 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1470336 (Python Code)

Max Activating Token Index: 710

Text #14

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9004. Min Act: -0.0000

Data Index: 748052 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1644046 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1143084 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8692. Min Act: -0.0000

Data Index: 820430 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8131. Min Act: -0.0000

Data Index: 897500 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.7469. Min Act: -0.0000

Data Index: 496697 (C4 (Web Text))

Max Activating Token Index: 172