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

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

Neuron 989 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3432. Min Act: -0.0003

Data Index: 959396 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2957. Min Act: -0.0003

Data Index: 39597 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3207. Min Act: -0.0003

Data Index: 848420 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3223. Min Act: -0.0003

Data Index: 724020 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3193. Min Act: -0.0003

Data Index: 202682 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3216. Min Act: -0.0003

Data Index: 560982 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2992. Min Act: -0.0003

Data Index: 1126061 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3037. Min Act: -0.0003

Data Index: 1325531 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3290. Min Act: -0.0003

Data Index: 1357017 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2830. Min Act: -0.0003

Data Index: 310193 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3220. Min Act: -0.0003

Data Index: 527891 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3096. Min Act: -0.0003

Data Index: 1019692 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2989. Min Act: -0.0003

Data Index: 286191 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3033. Min Act: -0.0003

Data Index: 1242166 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2958. Min Act: -0.0003

Data Index: 542350 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3003. Min Act: -0.0003

Data Index: 752426 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3052. Min Act: -0.0003

Data Index: 793114 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3045. Min Act: -0.0003

Data Index: 1299414 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3009. Min Act: -0.0003

Data Index: 1067121 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3109. Min Act: -0.0003

Data Index: 168740 (C4 (Web Text))

Max Activating Token Index: 815