Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 614 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.0559. Min Range: -5.0559

Max Act: 5.0559. Min Act: -0.0001

Data Index: 144024 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 5.0559. Min Range: -5.0559

Max Act: 4.5864. Min Act: -0.0000

Data Index: 192501 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 5.0559. Min Range: -5.0559

Max Act: 4.5737. Min Act: -0.0001

Data Index: 224061 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 5.0559. Min Range: -5.0559

Max Act: 4.5195. Min Act: -0.0000

Data Index: 1005385 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 5.0559. Min Range: -5.0559

Max Act: 4.7095. Min Act: -0.0001

Data Index: 98147 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 5.0559. Min Range: -5.0559

Max Act: 4.1048. Min Act: -0.0001

Data Index: 491345 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 5.0559. Min Range: -5.0559

Max Act: 4.4075. Min Act: -0.0000

Data Index: 216156 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 5.0559. Min Range: -5.0559

Max Act: 3.6349. Min Act: -0.0001

Data Index: 916816 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 5.0559. Min Range: -5.0559

Max Act: 4.0580. Min Act: -0.0001

Data Index: 553505 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 5.0559. Min Range: -5.0559

Max Act: 4.0132. Min Act: -0.0000

Data Index: 896571 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 5.0559. Min Range: -5.0559

Max Act: 3.7990. Min Act: -0.0001

Data Index: 479471 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 5.0559. Min Range: -5.0559

Max Act: 3.7764. Min Act: -0.0001

Data Index: 944771 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 5.0559. Min Range: -5.0559

Max Act: 3.6520. Min Act: -0.0001

Data Index: 516257 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 5.0559. Min Range: -5.0559

Max Act: 3.4267. Min Act: -0.0001

Data Index: 867963 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 5.0559. Min Range: -5.0559

Max Act: 3.7114. Min Act: -0.0001

Data Index: 877736 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 5.0559. Min Range: -5.0559

Max Act: 3.5741. Min Act: -0.0000

Data Index: 1335187 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 5.0559. Min Range: -5.0559

Max Act: 3.4246. Min Act: -0.0001

Data Index: 1215075 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 5.0559. Min Range: -5.0559

Max Act: 3.7079. Min Act: -0.0001

Data Index: 279331 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 5.0559. Min Range: -5.0559

Max Act: 3.1042. Min Act: -0.0000

Data Index: 1157238 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 5.0559. Min Range: -5.0559

Max Act: 3.5224. Min Act: -0.0001

Data Index: 1332050 (C4 (Web Text))

Max Activating Token Index: 931