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

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

Neuron 262 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6017. Min Range: -2.6017

Max Act: 2.6017. Min Act: -0.0000

Data Index: 961552 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.6508. Min Act: -0.0000

Data Index: 1280158 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.6476. Min Act: -0.0000

Data Index: 1180037 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.5936. Min Act: -0.0000

Data Index: 401743 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1042001 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.4726. Min Act: -0.0000

Data Index: 645263 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.4287. Min Act: -0.0000

Data Index: 22951 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.5121. Min Act: -0.0000

Data Index: 457484 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.4603. Min Act: -0.0000

Data Index: 839690 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.3707. Min Act: -0.0000

Data Index: 1185845 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.3764. Min Act: -0.0000

Data Index: 1329583 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.4522. Min Act: -0.0000

Data Index: 1146395 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.4474. Min Act: -0.0000

Data Index: 223184 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.4337. Min Act: -0.0000

Data Index: 166159 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.4117. Min Act: -0.0000

Data Index: 1338114 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.3866. Min Act: -0.0000

Data Index: 103599 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.3539. Min Act: -0.0000

Data Index: 818675 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.4303. Min Act: -0.0000

Data Index: 756212 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.4321. Min Act: -0.0000

Data Index: 787484 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 2.6017. Min Range: -2.6017

Max Act: 1.4345. Min Act: -0.0000

Data Index: 200372 (C4 (Web Text))

Max Activating Token Index: 719