Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4768 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.7535. Min Act: -0.0000

Data Index: 854456 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.7057. Min Act: -0.0000

Data Index: 999843 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6822. Min Act: -0.0000

Data Index: 721613 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6348. Min Act: -0.0000

Data Index: 597390 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6619. Min Act: -0.0000

Data Index: 548291 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6661. Min Act: -0.0000

Data Index: 197147 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6510. Min Act: -0.0000

Data Index: 747768 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6421. Min Act: -0.0000

Data Index: 967234 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6458. Min Act: 0.0000

Data Index: 293535 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6390. Min Act: -0.0000

Data Index: 573581 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1256751 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.5996. Min Act: -0.0000

Data Index: 314446 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6067. Min Act: 0.0001

Data Index: 643061 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6072. Min Act: -0.0000

Data Index: 8652 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.5163. Min Act: -0.0000

Data Index: 360948 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.5385. Min Act: 0.0000

Data Index: 533741 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.5407. Min Act: -0.0000

Data Index: 691902 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1207212 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.5293. Min Act: -0.0000

Data Index: 937436 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.5454. Min Act: -0.0000

Data Index: 628234 (C4 (Web Text))

Max Activating Token Index: 873