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

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

Neuron 432 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0824. Min Act: -0.0000

Data Index: 203213 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1243159 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1240315 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1225274 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1322285 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8932. Min Act: -0.0000

Data Index: 174009 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8069. Min Act: -0.0000

Data Index: 774949 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9746. Min Act: -0.0000

Data Index: 209443 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1124711 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1582815 (Python Code)

Max Activating Token Index: 522

Text #10

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8569. Min Act: -0.0000

Data Index: 374881 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1496142 (Python Code)

Max Activating Token Index: 791

Text #12

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8231. Min Act: -0.0000

Data Index: 648644 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.7956. Min Act: 0.0000

Data Index: 1466422 (Python Code)

Max Activating Token Index: 903

Text #14

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8386. Min Act: -0.0000

Data Index: 403351 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1181603 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1525978 (Python Code)

Max Activating Token Index: 492

Text #17

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.7858. Min Act: -0.0000

Data Index: 208980 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8776. Min Act: -0.0000

Data Index: 79576 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1344188 (C4 (Web Text))

Max Activating Token Index: 508