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

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

Neuron 613 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3521. Min Act: -0.0000

Data Index: 981241 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3490. Min Act: -0.0000

Data Index: 392245 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1090662 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3256. Min Act: -0.0000

Data Index: 886878 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1029063 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2882. Min Act: -0.0000

Data Index: 464621 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3064. Min Act: -0.0000

Data Index: 584666 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1227504 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2890. Min Act: -0.0001

Data Index: 1344625 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2999. Min Act: -0.0000

Data Index: 345674 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2785. Min Act: -0.0001

Data Index: 1344670 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2856. Min Act: -0.0000

Data Index: 863652 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2824. Min Act: -0.0000

Data Index: 861697 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1337529 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2726. Min Act: -0.0000

Data Index: 691657 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2691. Min Act: -0.0000

Data Index: 460698 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2661. Min Act: -0.0000

Data Index: 324733 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2719. Min Act: -0.0000

Data Index: 794333 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2542. Min Act: -0.0001

Data Index: 940138 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2691. Min Act: -0.0000

Data Index: 260115 (C4 (Web Text))

Max Activating Token Index: 342