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

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

Neuron 3935 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: 1.0883. Min Range: -1.0883

Max Act: 1.0883. Min Act: -0.0000

Data Index: 966217 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1274248 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1273582 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.8644. Min Act: -0.0000

Data Index: 619393 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1510588 (Python Code)

Max Activating Token Index: 778

Text #5

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1438118 (Python Code)

Max Activating Token Index: 788

Text #6

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.8449. Min Act: 0.0001

Data Index: 109365 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.8130. Min Act: -0.0000

Data Index: 864006 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1144065 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1257747 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1093525 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.7124. Min Act: -0.0000

Data Index: 271946 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.7519. Min Act: -0.0000

Data Index: 536095 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.7344. Min Act: -0.0000

Data Index: 387309 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.7550. Min Act: -0.0000

Data Index: 577998 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.7425. Min Act: -0.0000

Data Index: 750434 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1480013 (Python Code)

Max Activating Token Index: 914

Text #17

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.6726. Min Act: -0.0000

Data Index: 755651 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1449356 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 1.0883. Min Range: -1.0883

Max Act: 0.7009. Min Act: -0.0000

Data Index: 356528 (C4 (Web Text))

Max Activating Token Index: 233