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

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

Neuron 3732 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7798. Min Range: -3.7798

Max Act: 3.7798. Min Act: -0.0000

Data Index: 1618665 (Python Code)

Max Activating Token Index: 567

Text #1

Max Range: 3.7798. Min Range: -3.7798

Max Act: 3.4082. Min Act: -0.0000

Data Index: 1544747 (Python Code)

Max Activating Token Index: 879

Text #2

Max Range: 3.7798. Min Range: -3.7798

Max Act: 3.1517. Min Act: -0.0000

Data Index: 1531213 (Python Code)

Max Activating Token Index: 17

Text #3

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.8977. Min Act: -0.0000

Data Index: 1498155 (Python Code)

Max Activating Token Index: 978

Text #4

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.8873. Min Act: -0.0000

Data Index: 1376700 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 3.7798. Min Range: -3.7798

Max Act: 3.1301. Min Act: -0.0000

Data Index: 1441355 (Python Code)

Max Activating Token Index: 902

Text #6

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.8771. Min Act: -0.0000

Data Index: 1530186 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.9061. Min Act: -0.0000

Data Index: 1475925 (Python Code)

Max Activating Token Index: 754

Text #8

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.7762. Min Act: -0.0000

Data Index: 1523244 (Python Code)

Max Activating Token Index: 756

Text #9

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.7882. Min Act: -0.0000

Data Index: 1515783 (Python Code)

Max Activating Token Index: 530

Text #10

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.8057. Min Act: -0.0000

Data Index: 1389054 (Python Code)

Max Activating Token Index: 649

Text #11

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.7437. Min Act: -0.0000

Data Index: 1371950 (Python Code)

Max Activating Token Index: 669

Text #12

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.7103. Min Act: -0.0000

Data Index: 1389967 (Python Code)

Max Activating Token Index: 991

Text #13

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.8067. Min Act: -0.0000

Data Index: 1393020 (Python Code)

Max Activating Token Index: 483

Text #14

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.6450. Min Act: -0.0000

Data Index: 1469532 (Python Code)

Max Activating Token Index: 487

Text #15

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.6075. Min Act: -0.0000

Data Index: 1428936 (Python Code)

Max Activating Token Index: 668

Text #16

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.3240. Min Act: -0.0000

Data Index: 1566166 (Python Code)

Max Activating Token Index: 361

Text #17

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1444198 (Python Code)

Max Activating Token Index: 654

Text #18

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.3777. Min Act: -0.0000

Data Index: 1411296 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.1499. Min Act: -0.0000

Data Index: 1511908 (Python Code)

Max Activating Token Index: 427