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

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

Neuron 2117 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: 0.4002. Min Range: -0.4002

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1280941 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3706. Min Act: -0.0000

Data Index: 674242 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3771. Min Act: -0.0001

Data Index: 196565 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3450. Min Act: -0.0000

Data Index: 879067 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3174. Min Act: -0.0000

Data Index: 372183 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3179. Min Act: -0.0000

Data Index: 836954 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2986. Min Act: -0.0000

Data Index: 278865 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2891. Min Act: -0.0000

Data Index: 176724 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1100693 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3125. Min Act: -0.0001

Data Index: 671544 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1090255 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2992. Min Act: -0.0000

Data Index: 304741 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3078. Min Act: -0.0000

Data Index: 812863 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2977. Min Act: -0.0001

Data Index: 892290 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3056. Min Act: -0.0000

Data Index: 775714 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2878. Min Act: -0.0000

Data Index: 131080 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3018. Min Act: -0.0000

Data Index: 688742 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2909. Min Act: -0.0000

Data Index: 935495 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2818. Min Act: -0.0000

Data Index: 312097 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2881. Min Act: -0.0000

Data Index: 947070 (C4 (Web Text))

Max Activating Token Index: 641