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

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

Neuron 3259 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1888. Min Act: -0.0001

Data Index: 786371 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1581. Min Act: -0.0001

Data Index: 611892 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1614. Min Act: -0.0001

Data Index: 1000587 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1332374 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1529. Min Act: -0.0001

Data Index: 127867 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1615. Min Act: -0.0001

Data Index: 639301 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1011619 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1524. Min Act: -0.0001

Data Index: 333122 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1307867 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1291285 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1305231 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1533. Min Act: -0.0001

Data Index: 882705 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1429. Min Act: -0.0001

Data Index: 767532 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1462. Min Act: -0.0001

Data Index: 665073 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1504. Min Act: -0.0001

Data Index: 356568 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1409. Min Act: -0.0001

Data Index: 334668 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1069147 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1469. Min Act: -0.0001

Data Index: 292157 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1395. Min Act: -0.0001

Data Index: 564495 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1325184 (C4 (Web Text))

Max Activating Token Index: 26