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

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

Neuron 715 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.3360. Min Act: -0.0002

Data Index: 1143898 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.3324. Min Act: -0.0002

Data Index: 932308 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.3356. Min Act: -0.0001

Data Index: 653352 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.3014. Min Act: -0.0001

Data Index: 687198 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.3116. Min Act: -0.0001

Data Index: 844349 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.3050. Min Act: -0.0001

Data Index: 609565 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.3127. Min Act: -0.0001

Data Index: 807025 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2885. Min Act: -0.0001

Data Index: 1017488 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2995. Min Act: -0.0002

Data Index: 1280944 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2865. Min Act: -0.0002

Data Index: 764010 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2834. Min Act: -0.0002

Data Index: 155010 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2959. Min Act: -0.0001

Data Index: 573337 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.3018. Min Act: -0.0002

Data Index: 1340148 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2839. Min Act: -0.0001

Data Index: 1113149 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2808. Min Act: -0.0001

Data Index: 881405 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2796. Min Act: -0.0001

Data Index: 1210817 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2885. Min Act: -0.0002

Data Index: 380363 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2778. Min Act: -0.0002

Data Index: 705777 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2826. Min Act: -0.0002

Data Index: 481970 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2797. Min Act: -0.0002

Data Index: 613713 (C4 (Web Text))

Max Activating Token Index: 663