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

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

Neuron 809 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.6009. Min Act: -0.0001

Data Index: 966569 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5004. Min Act: -0.0001

Data Index: 516862 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4897. Min Act: -0.0001

Data Index: 954267 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4819. Min Act: -0.0001

Data Index: 837186 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4969. Min Act: -0.0001

Data Index: 245151 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4894. Min Act: -0.0001

Data Index: 784892 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4894. Min Act: 0.0001

Data Index: 487766 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4467. Min Act: -0.0000

Data Index: 703240 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4442. Min Act: 0.0001

Data Index: 121970 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4359. Min Act: -0.0001

Data Index: 695018 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4580. Min Act: -0.0001

Data Index: 106557 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4360. Min Act: -0.0001

Data Index: 631109 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4415. Min Act: -0.0001

Data Index: 648549 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4268. Min Act: -0.0001

Data Index: 581901 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4316. Min Act: -0.0001

Data Index: 982844 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4249. Min Act: -0.0001

Data Index: 815569 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4331. Min Act: 0.0001

Data Index: 432741 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4198. Min Act: -0.0001

Data Index: 695863 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4297. Min Act: 0.0001

Data Index: 533889 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4286. Min Act: -0.0001

Data Index: 327429 (C4 (Web Text))

Max Activating Token Index: 168