Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1825 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0957. Min Act: -0.0001

Data Index: 1618141 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0552. Min Act: -0.0001

Data Index: 1477193 (Python Code)

Max Activating Token Index: 423

Text #2

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9517. Min Act: -0.0001

Data Index: 1630696 (Python Code)

Max Activating Token Index: 965

Text #3

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0396. Min Act: -0.0001

Data Index: 1539658 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0263. Min Act: -0.0001

Data Index: 1449859 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0775. Min Act: -0.0001

Data Index: 1597264 (Python Code)

Max Activating Token Index: 931

Text #6

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9833. Min Act: -0.0001

Data Index: 1601820 (Python Code)

Max Activating Token Index: 912

Text #7

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9452. Min Act: -0.0001

Data Index: 1450540 (Python Code)

Max Activating Token Index: 201

Text #8

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9385. Min Act: -0.0001

Data Index: 1450085 (Python Code)

Max Activating Token Index: 1000

Text #9

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9648. Min Act: -0.0001

Data Index: 1635926 (Python Code)

Max Activating Token Index: 536

Text #10

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9826. Min Act: -0.0001

Data Index: 1383148 (Python Code)

Max Activating Token Index: 367

Text #11

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9822. Min Act: -0.0001

Data Index: 1574760 (Python Code)

Max Activating Token Index: 609

Text #12

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9699. Min Act: -0.0001

Data Index: 1537801 (Python Code)

Max Activating Token Index: 630

Text #13

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9152. Min Act: -0.0001

Data Index: 1423567 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9653. Min Act: -0.0001

Data Index: 1400935 (Python Code)

Max Activating Token Index: 553

Text #15

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9278. Min Act: -0.0001

Data Index: 1548522 (Python Code)

Max Activating Token Index: 330

Text #16

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.8971. Min Act: -0.0001

Data Index: 1604722 (Python Code)

Max Activating Token Index: 309

Text #17

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9483. Min Act: -0.0001

Data Index: 1560289 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.8634. Min Act: -0.0001

Data Index: 1511254 (Python Code)

Max Activating Token Index: 784

Text #19

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.8567. Min Act: -0.0001

Data Index: 1490817 (Python Code)

Max Activating Token Index: 578