Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 260 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1104250 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1503. Min Act: -0.0001

Data Index: 618855 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1550. Min Act: -0.0001

Data Index: 584387 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1613. Min Act: -0.0001

Data Index: 673837 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1673. Min Act: -0.0001

Data Index: 618332 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1268832 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1541. Min Act: -0.0001

Data Index: 666307 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1093291 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1214402 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1468. Min Act: -0.0001

Data Index: 700842 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1082960 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1375. Min Act: -0.0001

Data Index: 932253 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1111550 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1502. Min Act: -0.0001

Data Index: 555403 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1500. Min Act: -0.0001

Data Index: 371450 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1411. Min Act: -0.0001

Data Index: 807997 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1368. Min Act: -0.0001

Data Index: 206811 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1456. Min Act: -0.0001

Data Index: 255067 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1303. Min Act: -0.0001

Data Index: 369837 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1125310 (C4 (Web Text))

Max Activating Token Index: 417