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

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

Neuron 1981 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: 0.3697. Min Range: -0.3697

Max Act: 0.3697. Min Act: -0.0001

Data Index: 382638 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3509. Min Act: -0.0000

Data Index: 70913 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3388. Min Act: -0.0001

Data Index: 169302 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3319. Min Act: -0.0001

Data Index: 226640 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3336. Min Act: -0.0000

Data Index: 105905 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3206. Min Act: -0.0001

Data Index: 237173 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3137. Min Act: -0.0001

Data Index: 431512 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3001. Min Act: -0.0000

Data Index: 331613 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3065. Min Act: -0.0000

Data Index: 210286 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1033202 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2971. Min Act: -0.0001

Data Index: 1211861 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2902. Min Act: -0.0001

Data Index: 558596 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2989. Min Act: -0.0001

Data Index: 1024910 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2857. Min Act: -0.0001

Data Index: 408847 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2947. Min Act: -0.0000

Data Index: 377481 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3017. Min Act: -0.0001

Data Index: 991462 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2983. Min Act: -0.0001

Data Index: 331649 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1329720 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1291744 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2844. Min Act: -0.0000

Data Index: 654534 (C4 (Web Text))

Max Activating Token Index: 60