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

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

Neuron 5880 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1234940 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.9543. Min Act: -0.0000

Data Index: 19824 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7872. Min Act: -0.0000

Data Index: 248060 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1064882 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.8173. Min Act: -0.0000

Data Index: 854977 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7722. Min Act: -0.0000

Data Index: 438097 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7614. Min Act: -0.0000

Data Index: 480339 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1031774 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7241. Min Act: -0.0000

Data Index: 957155 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7667. Min Act: -0.0000

Data Index: 934869 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.6943. Min Act: -0.0000

Data Index: 173857 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1306105 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1092512 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.6675. Min Act: -0.0000

Data Index: 856378 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.6577. Min Act: -0.0000

Data Index: 776544 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1213624 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.6527. Min Act: -0.0000

Data Index: 96376 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1344927 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1342096 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.6438. Min Act: -0.0000

Data Index: 56115 (C4 (Web Text))

Max Activating Token Index: 969