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

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

Neuron 2468 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.5076. Min Act: -0.0001

Data Index: 1458029 (Python Code)

Max Activating Token Index: 105

Text #1

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.5078. Min Act: -0.0001

Data Index: 1399551 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.4426. Min Act: -0.0001

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.4219. Min Act: -0.0001

Data Index: 1471302 (Python Code)

Max Activating Token Index: 866

Text #4

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.4044. Min Act: -0.0001

Data Index: 1617315 (Python Code)

Max Activating Token Index: 198

Text #5

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.4252. Min Act: -0.0001

Data Index: 1453169 (Python Code)

Max Activating Token Index: 671

Text #6

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3971. Min Act: -0.0001

Data Index: 1591102 (Python Code)

Max Activating Token Index: 127

Text #7

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3813. Min Act: -0.0001

Data Index: 1617968 (Python Code)

Max Activating Token Index: 955

Text #8

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.4132. Min Act: -0.0001

Data Index: 339813 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3758. Min Act: -0.0001

Data Index: 1432402 (Python Code)

Max Activating Token Index: 115

Text #10

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3697. Min Act: -0.0001

Data Index: 1600456 (Python Code)

Max Activating Token Index: 800

Text #11

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.4111. Min Act: -0.0001

Data Index: 1490014 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3592. Min Act: -0.0001

Data Index: 1527702 (Python Code)

Max Activating Token Index: 267

Text #13

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3517. Min Act: -0.0001

Data Index: 1408014 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3806. Min Act: -0.0001

Data Index: 1425119 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3539. Min Act: -0.0001

Data Index: 614875 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3452. Min Act: -0.0001

Data Index: 1415670 (Python Code)

Max Activating Token Index: 712

Text #17

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3533. Min Act: -0.0001

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3582. Min Act: -0.0001

Data Index: 1648032 (Python Code)

Max Activating Token Index: 437

Text #19

Max Range: 0.5078. Min Range: -0.5078

Max Act: 0.3703. Min Act: -0.0001

Data Index: 195699 (C4 (Web Text))

Max Activating Token Index: 109