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

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

Neuron 804 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.9575. Min Act: -0.0000

Data Index: 284873 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.3508. Min Act: -0.0000

Data Index: 588818 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.3622. Min Act: -0.0000

Data Index: 1527668 (Python Code)

Max Activating Token Index: 210

Text #3

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.8944. Min Act: -0.0000

Data Index: 448139 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.8896. Min Act: -0.0000

Data Index: 537794 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.8826. Min Act: -0.0000

Data Index: 962325 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.7502. Min Act: -0.0000

Data Index: 399859 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.6434. Min Act: -0.0000

Data Index: 1485806 (Python Code)

Max Activating Token Index: 770

Text #8

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.7634. Min Act: -0.0000

Data Index: 1041162 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.5596. Min Act: -0.0000

Data Index: 1338007 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.6960. Min Act: -0.0000

Data Index: 1607495 (Python Code)

Max Activating Token Index: 101

Text #11

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.6869. Min Act: -0.0000

Data Index: 1645558 (Python Code)

Max Activating Token Index: 76

Text #12

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.6786. Min Act: -0.0000

Data Index: 579071 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.5527. Min Act: -0.0000

Data Index: 1286101 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.6027. Min Act: -0.0000

Data Index: 1222558 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.5989. Min Act: -0.0000

Data Index: 1538436 (Python Code)

Max Activating Token Index: 1020

Text #16

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.6042. Min Act: -0.0000

Data Index: 1491505 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.4436. Min Act: -0.0000

Data Index: 1386063 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.4425. Min Act: -0.0000

Data Index: 516836 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 3.9575. Min Range: -3.9575

Max Act: 2.7845. Min Act: -0.0000

Data Index: 1120218 (C4 (Web Text))

Max Activating Token Index: 998