Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2157 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1639605 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1346820 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0864. Min Act: -0.0001

Data Index: 168542 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0605. Min Act: -0.0000

Data Index: 949904 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0574. Min Act: -0.0001

Data Index: 401873 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1117274 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0579. Min Act: -0.0000

Data Index: 297634 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0576. Min Act: -0.0001

Data Index: 855448 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0662. Min Act: -0.0001

Data Index: 237807 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0502. Min Act: -0.0001

Data Index: 645344 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1599374 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1646076 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0540. Min Act: -0.0000

Data Index: 499099 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1239453 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1302786 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0458. Min Act: -0.0000

Data Index: 1245643 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0521. Min Act: -0.0001

Data Index: 350180 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0455. Min Act: -0.0000

Data Index: 1080424 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0499. Min Act: -0.0000

Data Index: 543944 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0535. Min Act: -0.0000

Data Index: 504950 (C4 (Web Text))

Max Activating Token Index: 1023