Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1348 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1964. Min Range: -1.1964

Max Act: 1.1964. Min Act: -0.0001

Data Index: 1383512 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 1.1964. Min Range: -1.1964

Max Act: 1.1900. Min Act: -0.0001

Data Index: 1654666 (Python Code)

Max Activating Token Index: 804

Text #2

Max Range: 1.1964. Min Range: -1.1964

Max Act: 1.1360. Min Act: -0.0001

Data Index: 1498368 (Python Code)

Max Activating Token Index: 546

Text #3

Max Range: 1.1964. Min Range: -1.1964

Max Act: 1.0356. Min Act: -0.0001

Data Index: 1458568 (Python Code)

Max Activating Token Index: 68

Text #4

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.9883. Min Act: -0.0001

Data Index: 1534124 (Python Code)

Max Activating Token Index: 938

Text #5

Max Range: 1.1964. Min Range: -1.1964

Max Act: 1.0476. Min Act: -0.0001

Data Index: 1629741 (Python Code)

Max Activating Token Index: 121

Text #6

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.9377. Min Act: -0.0001

Data Index: 1502785 (Python Code)

Max Activating Token Index: 293

Text #7

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.9336. Min Act: -0.0001

Data Index: 1655694 (Python Code)

Max Activating Token Index: 89

Text #8

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.9470. Min Act: -0.0001

Data Index: 1486650 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.9004. Min Act: -0.0001

Data Index: 1638634 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.8638. Min Act: -0.0001

Data Index: 1599595 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.8605. Min Act: -0.0001

Data Index: 1623196 (Python Code)

Max Activating Token Index: 503

Text #12

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.8290. Min Act: -0.0001

Data Index: 1383175 (Python Code)

Max Activating Token Index: 440

Text #13

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.8771. Min Act: -0.0001

Data Index: 1644795 (Python Code)

Max Activating Token Index: 53

Text #14

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.8455. Min Act: -0.0001

Data Index: 1555525 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.8696. Min Act: -0.0001

Data Index: 1619451 (Python Code)

Max Activating Token Index: 961

Text #16

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.8543. Min Act: -0.0001

Data Index: 1636247 (Python Code)

Max Activating Token Index: 511

Text #17

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.8595. Min Act: -0.0001

Data Index: 1374003 (Python Code)

Max Activating Token Index: 57

Text #18

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.7968. Min Act: -0.0001

Data Index: 1489099 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 1.1964. Min Range: -1.1964

Max Act: 0.8723. Min Act: -0.0001

Data Index: 1626996 (Python Code)

Max Activating Token Index: 154