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

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

Neuron 791 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.6900. Min Act: -0.0000

Data Index: 1562763 (Python Code)

Max Activating Token Index: 319

Text #1

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.9258. Min Act: -0.0000

Data Index: 1557772 (Python Code)

Max Activating Token Index: 465

Text #2

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.7582. Min Act: -0.0000

Data Index: 1539193 (Python Code)

Max Activating Token Index: 152

Text #3

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.1113. Min Act: -0.0000

Data Index: 1609203 (Python Code)

Max Activating Token Index: 122

Text #4

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.9595. Min Act: -0.0000

Data Index: 1399772 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.7989. Min Act: -0.0000

Data Index: 1487468 (Python Code)

Max Activating Token Index: 543

Text #6

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.9395. Min Act: -0.0000

Data Index: 1583557 (Python Code)

Max Activating Token Index: 482

Text #7

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.9290. Min Act: -0.0000

Data Index: 1481490 (Python Code)

Max Activating Token Index: 913

Text #8

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.7873. Min Act: -0.0000

Data Index: 1635528 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.8800. Min Act: -0.0000

Data Index: 1461163 (Python Code)

Max Activating Token Index: 143

Text #10

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.6066. Min Act: -0.0000

Data Index: 1567162 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.7330. Min Act: -0.0000

Data Index: 1537046 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.3137. Min Act: -0.0000

Data Index: 1379984 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.3008. Min Act: -0.0000

Data Index: 1385940 (Python Code)

Max Activating Token Index: 187

Text #14

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.5382. Min Act: -0.0000

Data Index: 1576586 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.4518. Min Act: -0.0000

Data Index: 1377650 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.4661. Min Act: -0.0000

Data Index: 1518110 (Python Code)

Max Activating Token Index: 644

Text #17

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.7359. Min Act: -0.0000

Data Index: 1415125 (Python Code)

Max Activating Token Index: 956

Text #18

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.6036. Min Act: -0.0000

Data Index: 1579284 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.2525. Min Act: -0.0000

Data Index: 1385550 (Python Code)

Max Activating Token Index: 494