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

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

Neuron 3036 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2150. Min Range: -1.2150

Max Act: 1.2150. Min Act: -0.0000

Data Index: 384568 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 1.2150. Min Range: -1.2150

Max Act: 1.1007. Min Act: -0.0000

Data Index: 81281 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 1.2150. Min Range: -1.2150

Max Act: 1.0644. Min Act: -0.0000

Data Index: 1064574 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 1.2150. Min Range: -1.2150

Max Act: 1.0010. Min Act: -0.0001

Data Index: 1152454 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 1.2150. Min Range: -1.2150

Max Act: 1.0569. Min Act: -0.0000

Data Index: 648800 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 1.2150. Min Range: -1.2150

Max Act: 1.0726. Min Act: -0.0000

Data Index: 407283 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.2150. Min Range: -1.2150

Max Act: 1.0034. Min Act: 0.0000

Data Index: 258024 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9670. Min Act: -0.0000

Data Index: 582599 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9829. Min Act: -0.0001

Data Index: 1327945 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9265. Min Act: -0.0001

Data Index: 1133258 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9752. Min Act: -0.0000

Data Index: 126886 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9983. Min Act: -0.0000

Data Index: 462443 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9864. Min Act: -0.0001

Data Index: 906582 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9567. Min Act: -0.0000

Data Index: 872266 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9814. Min Act: -0.0000

Data Index: 637112 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9352. Min Act: -0.0000

Data Index: 169549 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9034. Min Act: -0.0000

Data Index: 590192 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9392. Min Act: -0.0001

Data Index: 1150305 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.9339. Min Act: -0.0000

Data Index: 12656 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.8916. Min Act: -0.0000

Data Index: 1042586 (C4 (Web Text))

Max Activating Token Index: 697