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

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

Neuron 1049 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.7929. Min Act: -0.0001

Data Index: 1588744 (Python Code)

Max Activating Token Index: 486

Text #1

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.7682. Min Act: -0.0001

Data Index: 1500452 (Python Code)

Max Activating Token Index: 714

Text #2

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6488. Min Act: -0.0001

Data Index: 1613702 (Python Code)

Max Activating Token Index: 614

Text #3

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6361. Min Act: -0.0001

Data Index: 1529760 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6449. Min Act: -0.0001

Data Index: 1625087 (Python Code)

Max Activating Token Index: 575

Text #5

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6025. Min Act: -0.0001

Data Index: 1523964 (Python Code)

Max Activating Token Index: 929

Text #6

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5838. Min Act: -0.0001

Data Index: 1463328 (Python Code)

Max Activating Token Index: 785

Text #7

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5602. Min Act: -0.0001

Data Index: 1618680 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5297. Min Act: -0.0001

Data Index: 1551375 (Python Code)

Max Activating Token Index: 666

Text #9

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5045. Min Act: -0.0001

Data Index: 1518588 (Python Code)

Max Activating Token Index: 601

Text #10

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5178. Min Act: -0.0001

Data Index: 1468346 (Python Code)

Max Activating Token Index: 304

Text #11

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5536. Min Act: -0.0001

Data Index: 1437070 (Python Code)

Max Activating Token Index: 752

Text #12

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5141. Min Act: -0.0001

Data Index: 1606129 (Python Code)

Max Activating Token Index: 946

Text #13

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5564. Min Act: -0.0001

Data Index: 1575242 (Python Code)

Max Activating Token Index: 532

Text #14

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5364. Min Act: -0.0001

Data Index: 1476429 (Python Code)

Max Activating Token Index: 871

Text #15

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4934. Min Act: -0.0001

Data Index: 1647508 (Python Code)

Max Activating Token Index: 639

Text #16

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4521. Min Act: -0.0001

Data Index: 1529546 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1525108 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4418. Min Act: -0.0001

Data Index: 1592899 (Python Code)

Max Activating Token Index: 702

Text #19

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1361644 (Python Code)

Max Activating Token Index: 35