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

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

Neuron 4766 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: 0.8874. Min Range: -0.8874

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1466408 (Python Code)

Max Activating Token Index: 603

Text #1

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1586332 (Python Code)

Max Activating Token Index: 728

Text #2

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1583261 (Python Code)

Max Activating Token Index: 310

Text #3

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1587236 (Python Code)

Max Activating Token Index: 707

Text #4

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1606433 (Python Code)

Max Activating Token Index: 198

Text #5

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1653463 (Python Code)

Max Activating Token Index: 447

Text #6

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1595302 (Python Code)

Max Activating Token Index: 368

Text #7

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1602136 (Python Code)

Max Activating Token Index: 954

Text #8

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1376110 (Python Code)

Max Activating Token Index: 533

Text #9

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1493880 (Python Code)

Max Activating Token Index: 122

Text #10

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1509261 (Python Code)

Max Activating Token Index: 449

Text #11

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1432883 (Python Code)

Max Activating Token Index: 89

Text #12

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1469036 (Python Code)

Max Activating Token Index: 376

Text #13

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1627435 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1367849 (Python Code)

Max Activating Token Index: 818

Text #15

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1582491 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1623775 (Python Code)

Max Activating Token Index: 615

Text #17

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1513233 (Python Code)

Max Activating Token Index: 424

Text #18

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1510133 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1484500 (Python Code)

Max Activating Token Index: 517