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

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

Neuron 1848 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: 2.4307. Min Range: -2.4307

Max Act: 2.4307. Min Act: -0.0000

Data Index: 1491392 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 2.4307. Min Range: -2.4307

Max Act: 2.0713. Min Act: -0.0000

Data Index: 1449289 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 2.4307. Min Range: -2.4307

Max Act: 2.0158. Min Act: -0.0000

Data Index: 1619920 (Python Code)

Max Activating Token Index: 592

Text #3

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.9481. Min Act: -0.0000

Data Index: 1442823 (Python Code)

Max Activating Token Index: 965

Text #4

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.8835. Min Act: -0.0000

Data Index: 1554685 (Python Code)

Max Activating Token Index: 587

Text #5

Max Range: 2.4307. Min Range: -2.4307

Max Act: 2.0680. Min Act: -0.0000

Data Index: 1439340 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.6141. Min Act: -0.0000

Data Index: 1633810 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.6866. Min Act: 0.0000

Data Index: 1471823 (Python Code)

Max Activating Token Index: 518

Text #8

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.7629. Min Act: -0.0000

Data Index: 1549213 (Python Code)

Max Activating Token Index: 526

Text #9

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.6562. Min Act: -0.0000

Data Index: 1426891 (Python Code)

Max Activating Token Index: 615

Text #10

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.5386. Min Act: -0.0000

Data Index: 1637304 (Python Code)

Max Activating Token Index: 435

Text #11

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.5300. Min Act: -0.0000

Data Index: 1643774 (Python Code)

Max Activating Token Index: 377

Text #12

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.5073. Min Act: -0.0000

Data Index: 1430431 (Python Code)

Max Activating Token Index: 780

Text #13

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.6150. Min Act: -0.0000

Data Index: 1529297 (Python Code)

Max Activating Token Index: 190

Text #14

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.5966. Min Act: 0.0000

Data Index: 1546850 (Python Code)

Max Activating Token Index: 804

Text #15

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.6033. Min Act: -0.0000

Data Index: 1424403 (Python Code)

Max Activating Token Index: 832

Text #16

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.5726. Min Act: 0.0000

Data Index: 1560679 (Python Code)

Max Activating Token Index: 713

Text #17

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.5547. Min Act: 0.0000

Data Index: 1389682 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.4485. Min Act: -0.0000

Data Index: 1634182 (Python Code)

Max Activating Token Index: 500

Text #19

Max Range: 2.4307. Min Range: -2.4307

Max Act: 1.7081. Min Act: -0.0000

Data Index: 1444936 (Python Code)

Max Activating Token Index: 805