Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1069 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1161756 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1073126 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.5022. Min Act: -0.0000

Data Index: 519069 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4938. Min Act: -0.0001

Data Index: 930648 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.5189. Min Act: -0.0001

Data Index: 806752 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4787. Min Act: -0.0001

Data Index: 858139 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4885. Min Act: -0.0000

Data Index: 698140 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4868. Min Act: -0.0000

Data Index: 611599 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4700. Min Act: -0.0001

Data Index: 1082031 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4600. Min Act: -0.0001

Data Index: 1245272 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1336985 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4608. Min Act: -0.0001

Data Index: 754156 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4454. Min Act: -0.0000

Data Index: 522543 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1179529 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4256. Min Act: -0.0001

Data Index: 95187 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4318. Min Act: -0.0001

Data Index: 1101578 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1053376 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4062. Min Act: -0.0000

Data Index: 712742 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4042. Min Act: -0.0001

Data Index: 437616 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.3772. Min Act: -0.0000

Data Index: 605895 (C4 (Web Text))

Max Activating Token Index: 502