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

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

Neuron 370 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.3909. Min Act: -0.0000

Data Index: 707104 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.3778. Min Act: -0.0001

Data Index: 1118018 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.3369. Min Act: -0.0000

Data Index: 315514 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1023849 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.3073. Min Act: -0.0001

Data Index: 937436 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.3016. Min Act: -0.0001

Data Index: 91779 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1215763 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2878. Min Act: -0.0000

Data Index: 549455 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2964. Min Act: -0.0000

Data Index: 770363 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2972. Min Act: -0.0001

Data Index: 293535 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2968. Min Act: -0.0001

Data Index: 430275 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2964. Min Act: -0.0001

Data Index: 701553 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.3023. Min Act: -0.0001

Data Index: 30916 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2905. Min Act: -0.0001

Data Index: 1009193 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2892. Min Act: -0.0000

Data Index: 998219 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1257545 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1109762 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2853. Min Act: -0.0001

Data Index: 1060765 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2861. Min Act: -0.0000

Data Index: 791648 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.3909. Min Range: -0.3909

Max Act: 0.2836. Min Act: -0.0000

Data Index: 277623 (C4 (Web Text))

Max Activating Token Index: 83