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

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

Neuron 5734 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: 1.4279. Min Range: -1.4279

Max Act: 1.4279. Min Act: -0.0000

Data Index: 1372578 (Python Code)

Max Activating Token Index: 522

Text #1

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1475778 (Python Code)

Max Activating Token Index: 92

Text #2

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.2063. Min Act: -0.0000

Data Index: 1536674 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1556692 (Python Code)

Max Activating Token Index: 949

Text #4

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1540382 (Python Code)

Max Activating Token Index: 501

Text #5

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1367320 (Python Code)

Max Activating Token Index: 62

Text #6

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1558297 (Python Code)

Max Activating Token Index: 840

Text #7

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.0302. Min Act: -0.0000

Data Index: 1533317 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 1.4279. Min Range: -1.4279

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1628216 (Python Code)

Max Activating Token Index: 194

Text #9

Max Range: 1.4279. Min Range: -1.4279

Max Act: 0.9647. Min Act: -0.0000

Data Index: 1537616 (Python Code)

Max Activating Token Index: 487

Text #10

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1615896 (Python Code)

Max Activating Token Index: 362

Text #11

Max Range: 1.4279. Min Range: -1.4279

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1626265 (Python Code)

Max Activating Token Index: 951

Text #12

Max Range: 1.4279. Min Range: -1.4279

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1400240 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 1.4279. Min Range: -1.4279

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1635069 (Python Code)

Max Activating Token Index: 250

Text #14

Max Range: 1.4279. Min Range: -1.4279

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1531643 (Python Code)

Max Activating Token Index: 402

Text #15

Max Range: 1.4279. Min Range: -1.4279

Max Act: 0.8817. Min Act: -0.0000

Data Index: 1613104 (Python Code)

Max Activating Token Index: 83

Text #16

Max Range: 1.4279. Min Range: -1.4279

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1428308 (Python Code)

Max Activating Token Index: 362

Text #17

Max Range: 1.4279. Min Range: -1.4279

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1421164 (Python Code)

Max Activating Token Index: 560

Text #18

Max Range: 1.4279. Min Range: -1.4279

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1636793 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 1.4279. Min Range: -1.4279

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1597209 (Python Code)

Max Activating Token Index: 201