Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3791 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.6207. Min Act: -0.0001

Data Index: 1646426 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5661. Min Act: -0.0001

Data Index: 1575815 (Python Code)

Max Activating Token Index: 179

Text #2

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5009. Min Act: -0.0002

Data Index: 1453448 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1515484 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1605431 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1483149 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1403122 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1421882 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4873. Min Act: -0.0001

Data Index: 1523029 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4795. Min Act: -0.0001

Data Index: 1370155 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1573189 (Python Code)

Max Activating Token Index: 690

Text #11

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4518. Min Act: -0.0001

Data Index: 1549045 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4541. Min Act: -0.0001

Data Index: 1480064 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4632. Min Act: -0.0001

Data Index: 1473135 (Python Code)

Max Activating Token Index: 106

Text #14

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4476. Min Act: -0.0001

Data Index: 1583602 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4562. Min Act: -0.0002

Data Index: 437484 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4270. Min Act: -0.0001

Data Index: 1635036 (Python Code)

Max Activating Token Index: 124

Text #17

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4216. Min Act: -0.0001

Data Index: 1386224 (Python Code)

Max Activating Token Index: 654

Text #18

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4341. Min Act: -0.0001

Data Index: 1573785 (Python Code)

Max Activating Token Index: 278

Text #19

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4176. Min Act: -0.0001

Data Index: 1499946 (Python Code)

Max Activating Token Index: 103