Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 957 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.4966. Min Act: -0.0000

Data Index: 31500 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1546399 (Python Code)

Max Activating Token Index: 808

Text #2

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.2735. Min Act: -0.0000

Data Index: 54632 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1607200 (Python Code)

Max Activating Token Index: 296

Text #4

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1629359 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1475821 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1074120 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.8940. Min Act: -0.0000

Data Index: 85451 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1415972 (Python Code)

Max Activating Token Index: 198

Text #9

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1457934 (Python Code)

Max Activating Token Index: 801

Text #10

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1449302 (Python Code)

Max Activating Token Index: 792

Text #11

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1383518 (Python Code)

Max Activating Token Index: 946

Text #12

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1582045 (Python Code)

Max Activating Token Index: 226

Text #13

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.8583. Min Act: -0.0000

Data Index: 832511 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1390117 (Python Code)

Max Activating Token Index: 647

Text #15

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.7329. Min Act: -0.0000

Data Index: 590684 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1518305 (Python Code)

Max Activating Token Index: 651

Text #17

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1033480 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1442683 (Python Code)

Max Activating Token Index: 488

Text #19

Max Range: 1.4966. Min Range: -1.4966

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1568855 (Python Code)

Max Activating Token Index: 322