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

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

Neuron 3224 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.9331. Min Act: -0.0001

Data Index: 1206969 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 4.1136. Min Range: -4.1136

Max Act: 4.0832. Min Act: -0.0001

Data Index: 121801 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 4.1136. Min Range: -4.1136

Max Act: 4.0396. Min Act: -0.0000

Data Index: 328004 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.9522. Min Act: -0.0001

Data Index: 150366 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 4.1136. Min Range: -4.1136

Max Act: 4.1136. Min Act: -0.0001

Data Index: 832818 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.8405. Min Act: -0.0001

Data Index: 1042368 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.6262. Min Act: -0.0001

Data Index: 318123 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.4511. Min Act: -0.0001

Data Index: 80095 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.8987. Min Act: -0.0000

Data Index: 734169 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.3241. Min Act: -0.0001

Data Index: 531491 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.3415. Min Act: -0.0001

Data Index: 243546 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.3551. Min Act: -0.0001

Data Index: 952616 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.5424. Min Act: -0.0001

Data Index: 1287363 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.5346. Min Act: -0.0001

Data Index: 1232331 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.3071. Min Act: -0.0001

Data Index: 508253 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.3858. Min Act: -0.0000

Data Index: 1070349 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.5844. Min Act: -0.0001

Data Index: 824400 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.4275. Min Act: -0.0000

Data Index: 1078955 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.3738. Min Act: -0.0001

Data Index: 722134 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 4.1136. Min Range: -4.1136

Max Act: 3.3598. Min Act: -0.0001

Data Index: 870263 (C4 (Web Text))

Max Activating Token Index: 333