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

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

Neuron 169 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0571. Min Act: -0.0000

Data Index: 573258 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1588753 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0565. Min Act: -0.0000

Data Index: 1236031 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1508013 (Python Code)

Max Activating Token Index: 365

Text #4

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1023908 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1643573 (Python Code)

Max Activating Token Index: 115

Text #6

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0543. Min Act: -0.0000

Data Index: 242448 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1651234 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0527. Min Act: -0.0000

Data Index: 627995 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0475. Min Act: -0.0000

Data Index: 77910 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0466. Min Act: -0.0000

Data Index: 944692 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0408. Min Act: -0.0000

Data Index: 216121 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1134926 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0462. Min Act: -0.0000

Data Index: 1432589 (Python Code)

Max Activating Token Index: 68

Text #14

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0485. Min Act: -0.0000

Data Index: 199622 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0461. Min Act: -0.0000

Data Index: 837646 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1056024 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0429. Min Act: -0.0000

Data Index: 705827 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0452. Min Act: -0.0000

Data Index: 124300 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1014931 (C4 (Web Text))

Max Activating Token Index: 738