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

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

Neuron 5039 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1025290 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3931. Min Act: -0.0000

Data Index: 720378 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3822. Min Act: -0.0000

Data Index: 338527 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3690. Min Act: -0.0000

Data Index: 225692 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1181310 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3621. Min Act: -0.0000

Data Index: 321951 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3739. Min Act: -0.0000

Data Index: 706111 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1343804 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3600. Min Act: -0.0000

Data Index: 188935 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3586. Min Act: -0.0000

Data Index: 425587 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1196545 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1328797 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3523. Min Act: -0.0000

Data Index: 243619 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1301480 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1358474 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3431. Min Act: -0.0000

Data Index: 171293 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3401. Min Act: -0.0000

Data Index: 859408 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3423. Min Act: -0.0000

Data Index: 163884 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3512. Min Act: -0.0000

Data Index: 601619 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3165. Min Act: -0.0000

Data Index: 719257 (C4 (Web Text))

Max Activating Token Index: 320