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

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

Neuron 1658 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8381. Min Range: -3.8381

Max Act: 3.8381. Min Act: 0.0000

Data Index: 1650654 (Python Code)

Max Activating Token Index: 157

Text #1

Max Range: 3.8381. Min Range: -3.8381

Max Act: 3.3576. Min Act: -0.0000

Data Index: 1465115 (Python Code)

Max Activating Token Index: 1005

Text #2

Max Range: 3.8381. Min Range: -3.8381

Max Act: 3.4268. Min Act: -0.0000

Data Index: 1577230 (Python Code)

Max Activating Token Index: 227

Text #3

Max Range: 3.8381. Min Range: -3.8381

Max Act: 3.1672. Min Act: -0.0000

Data Index: 1426066 (Python Code)

Max Activating Token Index: 635

Text #4

Max Range: 3.8381. Min Range: -3.8381

Max Act: 3.2349. Min Act: -0.0000

Data Index: 1418541 (Python Code)

Max Activating Token Index: 849

Text #5

Max Range: 3.8381. Min Range: -3.8381

Max Act: 3.2112. Min Act: -0.0000

Data Index: 1519489 (Python Code)

Max Activating Token Index: 413

Text #6

Max Range: 3.8381. Min Range: -3.8381

Max Act: 3.1953. Min Act: -0.0000

Data Index: 1553444 (Python Code)

Max Activating Token Index: 156

Text #7

Max Range: 3.8381. Min Range: -3.8381

Max Act: 3.0980. Min Act: -0.0000

Data Index: 1655289 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 3.8381. Min Range: -3.8381

Max Act: 3.0604. Min Act: -0.0000

Data Index: 1592622 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 3.8381. Min Range: -3.8381

Max Act: 2.7566. Min Act: -0.0000

Data Index: 1576338 (Python Code)

Max Activating Token Index: 285

Text #10

Max Range: 3.8381. Min Range: -3.8381

Max Act: 2.8498. Min Act: -0.0000

Data Index: 1562999 (Python Code)

Max Activating Token Index: 503

Text #11

Max Range: 3.8381. Min Range: -3.8381

Max Act: 2.7934. Min Act: -0.0000

Data Index: 1363108 (Python Code)

Max Activating Token Index: 47

Text #12

Max Range: 3.8381. Min Range: -3.8381

Max Act: 2.7953. Min Act: -0.0000

Data Index: 1421812 (Python Code)

Max Activating Token Index: 79

Text #13

Max Range: 3.8381. Min Range: -3.8381

Max Act: 2.7829. Min Act: -0.0000

Data Index: 1446175 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 3.8381. Min Range: -3.8381

Max Act: 2.6328. Min Act: -0.0000

Data Index: 1407223 (Python Code)

Max Activating Token Index: 825

Text #15

Max Range: 3.8381. Min Range: -3.8381

Max Act: 2.7476. Min Act: -0.0000

Data Index: 1407957 (Python Code)

Max Activating Token Index: 929

Text #16

Max Range: 3.8381. Min Range: -3.8381

Max Act: 2.7611. Min Act: -0.0000

Data Index: 1648080 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 3.8381. Min Range: -3.8381

Max Act: 2.6105. Min Act: -0.0000

Data Index: 1546797 (Python Code)

Max Activating Token Index: 752

Text #18

Max Range: 3.8381. Min Range: -3.8381

Max Act: 2.7528. Min Act: -0.0000

Data Index: 1414171 (Python Code)

Max Activating Token Index: 381

Text #19

Max Range: 3.8381. Min Range: -3.8381

Max Act: 2.8895. Min Act: -0.0000

Data Index: 1384850 (Python Code)

Max Activating Token Index: 791