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

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

Neuron 3144 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1470. Min Range: -5.1470

Max Act: 5.1470. Min Act: -0.0001

Data Index: 1322818 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 5.1470. Min Range: -5.1470

Max Act: 3.1305. Min Act: -0.0001

Data Index: 105701 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 5.1470. Min Range: -5.1470

Max Act: 2.8427. Min Act: -0.0001

Data Index: 955888 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 5.1470. Min Range: -5.1470

Max Act: 2.4069. Min Act: -0.0001

Data Index: 468783 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 5.1470. Min Range: -5.1470

Max Act: 2.1961. Min Act: -0.0000

Data Index: 911340 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.4152. Min Act: -0.0001

Data Index: 1165802 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.3544. Min Act: -0.0001

Data Index: 1210077 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.6071. Min Act: -0.0001

Data Index: 370878 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.4434. Min Act: -0.0001

Data Index: 763220 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.3823. Min Act: -0.0001

Data Index: 327777 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.0908. Min Act: -0.0001

Data Index: 712930 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.3987. Min Act: -0.0000

Data Index: 542799 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.2001. Min Act: -0.0001

Data Index: 98580 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.3929. Min Act: -0.0001

Data Index: 1282912 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.2372. Min Act: -0.0001

Data Index: 163407 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.3037. Min Act: -0.0001

Data Index: 1026248 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.1245. Min Act: -0.0001

Data Index: 889348 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.2866. Min Act: -0.0001

Data Index: 1105978 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.3302. Min Act: -0.0001

Data Index: 688397 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 5.1470. Min Range: -5.1470

Max Act: 1.0746. Min Act: -0.0001

Data Index: 661005 (C4 (Web Text))

Max Activating Token Index: 292