Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 614 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4549. Min Act: -0.0001

Data Index: 769898 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3788. Min Act: -0.0001

Data Index: 395806 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3747. Min Act: -0.0001

Data Index: 704810 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3345. Min Act: -0.0001

Data Index: 789627 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.2995. Min Act: -0.0001

Data Index: 12791 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3197. Min Act: -0.0001

Data Index: 41538 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.2956. Min Act: -0.0001

Data Index: 288698 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.2930. Min Act: -0.0001

Data Index: 992498 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3128. Min Act: -0.0001

Data Index: 858700 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3010. Min Act: -0.0001

Data Index: 522776 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.2905. Min Act: -0.0001

Data Index: 157294 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.2993. Min Act: -0.0001

Data Index: 9134 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3320. Min Act: -0.0001

Data Index: 988410 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3063. Min Act: -0.0001

Data Index: 159408 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3143. Min Act: -0.0001

Data Index: 1076067 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3062. Min Act: -0.0001

Data Index: 834264 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.2950. Min Act: -0.0001

Data Index: 1143055 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.2816. Min Act: -0.0001

Data Index: 679161 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3017. Min Act: -0.0001

Data Index: 1246621 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.2811. Min Act: -0.0001

Data Index: 645080 (C4 (Web Text))

Max Activating Token Index: 340