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

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

Neuron 5007 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.7743. Min Act: -0.0000

Data Index: 1604202 (Python Code)

Max Activating Token Index: 351

Text #1

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.6166. Min Act: -0.0000

Data Index: 1601060 (Python Code)

Max Activating Token Index: 278

Text #2

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5883. Min Act: -0.0000

Data Index: 1578044 (Python Code)

Max Activating Token Index: 237

Text #3

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5753. Min Act: -0.0000

Data Index: 1640295 (Python Code)

Max Activating Token Index: 284

Text #4

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.3861. Min Act: -0.0000

Data Index: 1407344 (Python Code)

Max Activating Token Index: 785

Text #5

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.3596. Min Act: -0.0000

Data Index: 1575668 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1370449 (Python Code)

Max Activating Token Index: 198

Text #7

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.4435. Min Act: -0.0000

Data Index: 1379929 (Python Code)

Max Activating Token Index: 350

Text #8

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.3091. Min Act: -0.0000

Data Index: 1363129 (Python Code)

Max Activating Token Index: 215

Text #9

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.3581. Min Act: -0.0000

Data Index: 1490524 (Python Code)

Max Activating Token Index: 1010

Text #10

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.4356. Min Act: -0.0000

Data Index: 1366260 (Python Code)

Max Activating Token Index: 632

Text #11

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.3242. Min Act: -0.0000

Data Index: 1518032 (Python Code)

Max Activating Token Index: 474

Text #12

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.2851. Min Act: -0.0000

Data Index: 1555630 (Python Code)

Max Activating Token Index: 875

Text #13

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.4237. Min Act: -0.0000

Data Index: 1433649 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1371630 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.3014. Min Act: -0.0000

Data Index: 1575113 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.3367. Min Act: -0.0000

Data Index: 1521912 (Python Code)

Max Activating Token Index: 464

Text #17

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.3459. Min Act: -0.0000

Data Index: 1429002 (Python Code)

Max Activating Token Index: 539

Text #18

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1522070 (Python Code)

Max Activating Token Index: 186

Text #19

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.4108. Min Act: -0.0000

Data Index: 1598882 (Python Code)

Max Activating Token Index: 779