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

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

Neuron 2301 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: 1.6935. Min Range: -1.6935

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1627866 (Python Code)

Max Activating Token Index: 447

Text #1

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.6935. Min Act: -0.0000

Data Index: 1627118 (Python Code)

Max Activating Token Index: 50

Text #2

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5661. Min Act: -0.0000

Data Index: 1370255 (Python Code)

Max Activating Token Index: 163

Text #3

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5779. Min Act: -0.0000

Data Index: 1469000 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4640. Min Act: -0.0000

Data Index: 1480621 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3747. Min Act: -0.0000

Data Index: 1377484 (Python Code)

Max Activating Token Index: 694

Text #6

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3654. Min Act: -0.0000

Data Index: 1366344 (Python Code)

Max Activating Token Index: 105

Text #7

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3162. Min Act: -0.0000

Data Index: 1651643 (Python Code)

Max Activating Token Index: 107

Text #8

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1455597 (Python Code)

Max Activating Token Index: 502

Text #9

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.1935. Min Act: -0.0000

Data Index: 1368284 (Python Code)

Max Activating Token Index: 424

Text #10

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3019. Min Act: -0.0000

Data Index: 1560234 (Python Code)

Max Activating Token Index: 394

Text #11

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.2427. Min Act: -0.0000

Data Index: 1433768 (Python Code)

Max Activating Token Index: 440

Text #12

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1564960 (Python Code)

Max Activating Token Index: 456

Text #13

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1636143 (Python Code)

Max Activating Token Index: 484

Text #14

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1365055 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1558577 (Python Code)

Max Activating Token Index: 424

Text #16

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.1752. Min Act: -0.0000

Data Index: 1481054 (Python Code)

Max Activating Token Index: 326

Text #17

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1503432 (Python Code)

Max Activating Token Index: 290

Text #18

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1622855 (Python Code)

Max Activating Token Index: 404

Text #19

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1426864 (Python Code)

Max Activating Token Index: 149