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

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

Neuron 1232 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: 1.0057. Min Range: -1.0057

Max Act: 1.0057. Min Act: -0.0001

Data Index: 543985 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.9259. Min Act: -0.0001

Data Index: 337326 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8268. Min Act: -0.0001

Data Index: 510379 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8711. Min Act: -0.0001

Data Index: 892444 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8591. Min Act: -0.0001

Data Index: 1140492 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8069. Min Act: -0.0001

Data Index: 1109532 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.6415. Min Act: -0.0001

Data Index: 921313 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7733. Min Act: -0.0001

Data Index: 1324681 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7527. Min Act: -0.0001

Data Index: 1057716 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7430. Min Act: -0.0001

Data Index: 1329460 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7702. Min Act: -0.0001

Data Index: 334596 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7016. Min Act: -0.0001

Data Index: 398011 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7225. Min Act: -0.0001

Data Index: 434920 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.6878. Min Act: -0.0001

Data Index: 990821 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.6392. Min Act: -0.0001

Data Index: 980876 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.6243. Min Act: -0.0001

Data Index: 38617 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.6248. Min Act: -0.0001

Data Index: 916405 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7039. Min Act: -0.0001

Data Index: 501178 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.6374. Min Act: -0.0001

Data Index: 558508 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.6995. Min Act: -0.0001

Data Index: 695366 (C4 (Web Text))

Max Activating Token Index: 661