Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1129 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.4324. Min Act: -0.0000

Data Index: 365214 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1588802 (Python Code)

Max Activating Token Index: 451

Text #2

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3902. Min Act: -0.0000

Data Index: 180788 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3779. Min Act: -0.0000

Data Index: 342652 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1385670 (Python Code)

Max Activating Token Index: 629

Text #5

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1403828 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1408898 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3505. Min Act: -0.0000

Data Index: 458045 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3409. Min Act: -0.0000

Data Index: 332222 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1620614 (Python Code)

Max Activating Token Index: 565

Text #10

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1529527 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1504254 (Python Code)

Max Activating Token Index: 502

Text #12

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3249. Min Act: -0.0001

Data Index: 1654805 (Python Code)

Max Activating Token Index: 746

Text #13

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3228. Min Act: -0.0000

Data Index: 990135 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3347. Min Act: -0.0000

Data Index: 259745 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1648620 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1505573 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3197. Min Act: -0.0000

Data Index: 932159 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3022. Min Act: -0.0000

Data Index: 50150 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1070366 (C4 (Web Text))

Max Activating Token Index: 134