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

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

Neuron 900 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6640. Min Act: -0.0000

Data Index: 287539 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5311. Min Act: -0.0000

Data Index: 604889 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4980. Min Act: 0.0001

Data Index: 992574 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1235234 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4455. Min Act: -0.0000

Data Index: 410204 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4754. Min Act: 0.0001

Data Index: 913827 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4284. Min Act: -0.0000

Data Index: 801868 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1236432 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4712. Min Act: -0.0000

Data Index: 888203 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1111499 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4254. Min Act: -0.0000

Data Index: 833895 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4244. Min Act: -0.0000

Data Index: 136426 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4004. Min Act: -0.0000

Data Index: 300243 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4314. Min Act: 0.0001

Data Index: 1283200 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4129. Min Act: -0.0000

Data Index: 89317 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4103. Min Act: 0.0000

Data Index: 167269 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3896. Min Act: -0.0000

Data Index: 536786 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3971. Min Act: 0.0000

Data Index: 1181907 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1337871 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3785. Min Act: -0.0000

Data Index: 909583 (C4 (Web Text))

Max Activating Token Index: 262