Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2230 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.5984. Min Act: -0.0001

Data Index: 1427281 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2338. Min Act: -0.0001

Data Index: 813601 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1795. Min Act: -0.0001

Data Index: 562429 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.4012. Min Act: -0.0001

Data Index: 1095551 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2937. Min Act: -0.0001

Data Index: 1172450 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2156. Min Act: -0.0001

Data Index: 482925 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1509. Min Act: -0.0001

Data Index: 1196464 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.4029. Min Act: -0.0000

Data Index: 773358 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2684. Min Act: -0.0001

Data Index: 829798 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2541. Min Act: -0.0001

Data Index: 531974 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.0806. Min Act: -0.0001

Data Index: 416433 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.5984. Min Range: -1.5984

Max Act: 0.9222. Min Act: -0.0001

Data Index: 96326 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2119. Min Act: -0.0001

Data Index: 256066 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1181. Min Act: -0.0001

Data Index: 532767 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1467. Min Act: -0.0001

Data Index: 786963 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1053. Min Act: -0.0001

Data Index: 710179 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1735. Min Act: -0.0001

Data Index: 101497 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1026. Min Act: -0.0001

Data Index: 1167904 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2363. Min Act: -0.0001

Data Index: 1271151 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 1.5984. Min Range: -1.5984

Max Act: 0.9801. Min Act: -0.0001

Data Index: 224642 (C4 (Web Text))

Max Activating Token Index: 838