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

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

Neuron 1199 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: 1.7249. Min Range: -1.7249

Max Act: 1.7249. Min Act: -0.0000

Data Index: 281331 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.5606. Min Act: -0.0000

Data Index: 1329877 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.5575. Min Act: -0.0000

Data Index: 1324747 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.7180. Min Act: -0.0000

Data Index: 212174 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.5309. Min Act: -0.0000

Data Index: 1057920 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.4199. Min Act: -0.0000

Data Index: 619521 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.3119. Min Act: -0.0000

Data Index: 910383 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.3827. Min Act: -0.0000

Data Index: 245302 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.2892. Min Act: -0.0000

Data Index: 501674 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.2604. Min Act: -0.0000

Data Index: 615046 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.2784. Min Act: -0.0000

Data Index: 1291320 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.2574. Min Act: -0.0000

Data Index: 20076 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.2152. Min Act: -0.0000

Data Index: 1141935 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.1553. Min Act: -0.0000

Data Index: 734068 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.2308. Min Act: -0.0000

Data Index: 602127 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.0907. Min Act: -0.0000

Data Index: 428243 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1184150 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.1950. Min Act: -0.0000

Data Index: 604150 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.2963. Min Act: -0.0000

Data Index: 1220120 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 1.7249. Min Range: -1.7249

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1327883 (C4 (Web Text))

Max Activating Token Index: 400