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

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

Neuron 5467 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: 0.5947. Min Range: -0.5947

Max Act: 0.5802. Min Act: -0.0001

Data Index: 1499006 (Python Code)

Max Activating Token Index: 243

Text #1

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5826. Min Act: -0.0001

Data Index: 1386059 (Python Code)

Max Activating Token Index: 810

Text #2

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5947. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5846. Min Act: -0.0001

Data Index: 1643817 (Python Code)

Max Activating Token Index: 584

Text #4

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5370. Min Act: -0.0001

Data Index: 1400381 (Python Code)

Max Activating Token Index: 566

Text #5

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5741. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5708. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5512. Min Act: -0.0001

Data Index: 1608547 (Python Code)

Max Activating Token Index: 204

Text #8

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5289. Min Act: -0.0001

Data Index: 1514863 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4998. Min Act: -0.0001

Data Index: 1363670 (Python Code)

Max Activating Token Index: 191

Text #10

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4807. Min Act: -0.0001

Data Index: 1488368 (Python Code)

Max Activating Token Index: 932

Text #11

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5112. Min Act: -0.0001

Data Index: 1509581 (Python Code)

Max Activating Token Index: 524

Text #12

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5002. Min Act: -0.0001

Data Index: 1566166 (Python Code)

Max Activating Token Index: 647

Text #13

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5108. Min Act: -0.0001

Data Index: 1511487 (Python Code)

Max Activating Token Index: 338

Text #14

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5026. Min Act: -0.0001

Data Index: 1652060 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5193. Min Act: -0.0001

Data Index: 1656894 (Python Code)

Max Activating Token Index: 926

Text #16

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4873. Min Act: -0.0001

Data Index: 1606869 (Python Code)

Max Activating Token Index: 871

Text #17

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4862. Min Act: -0.0001

Data Index: 1412237 (Python Code)

Max Activating Token Index: 362

Text #18

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4868. Min Act: -0.0001

Data Index: 1491470 (Python Code)

Max Activating Token Index: 901

Text #19

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4927. Min Act: -0.0001

Data Index: 1399671 (Python Code)

Max Activating Token Index: 555