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

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

Neuron 2039 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: 2.5340. Min Range: -2.5340

Max Act: 2.5340. Min Act: -0.0000

Data Index: 1567220 (Python Code)

Max Activating Token Index: 204

Text #1

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.6779. Min Act: -0.0000

Data Index: 1390217 (Python Code)

Max Activating Token Index: 166

Text #2

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.6019. Min Act: -0.0000

Data Index: 1570779 (Python Code)

Max Activating Token Index: 210

Text #3

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.3901. Min Act: -0.0000

Data Index: 1434688 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.3183. Min Act: -0.0000

Data Index: 1635771 (Python Code)

Max Activating Token Index: 107

Text #5

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.3499. Min Act: -0.0000

Data Index: 1572441 (Python Code)

Max Activating Token Index: 200

Text #6

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1626429 (Python Code)

Max Activating Token Index: 78

Text #7

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.3693. Min Act: -0.0000

Data Index: 1454102 (Python Code)

Max Activating Token Index: 47

Text #8

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.3269. Min Act: -0.0000

Data Index: 1480421 (Python Code)

Max Activating Token Index: 82

Text #9

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.2675. Min Act: -0.0000

Data Index: 1589967 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1568726 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1496359 (Python Code)

Max Activating Token Index: 640

Text #12

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.2607. Min Act: -0.0000

Data Index: 1378634 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1540767 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1656179 (Python Code)

Max Activating Token Index: 87

Text #15

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.2652. Min Act: -0.0000

Data Index: 1566016 (Python Code)

Max Activating Token Index: 81

Text #16

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.2566. Min Act: -0.0000

Data Index: 1541799 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1641355 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.2617. Min Act: -0.0000

Data Index: 1589732 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 2.5340. Min Range: -2.5340

Max Act: 1.2550. Min Act: -0.0000

Data Index: 1588117 (Python Code)

Max Activating Token Index: 92