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

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

Neuron 4901 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.9721. Min Act: -0.0001

Data Index: 1601072 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.9983. Min Act: -0.0001

Data Index: 1628462 (Python Code)

Max Activating Token Index: 959

Text #2

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.8358. Min Act: -0.0000

Data Index: 1496484 (Python Code)

Max Activating Token Index: 275

Text #3

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.8251. Min Act: -0.0000

Data Index: 1387063 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.6919. Min Act: -0.0000

Data Index: 1465005 (Python Code)

Max Activating Token Index: 538

Text #5

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.8521. Min Act: -0.0000

Data Index: 1635657 (Python Code)

Max Activating Token Index: 223

Text #6

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.7465. Min Act: -0.0000

Data Index: 1482606 (Python Code)

Max Activating Token Index: 207

Text #7

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.7523. Min Act: -0.0000

Data Index: 1454050 (Python Code)

Max Activating Token Index: 711

Text #8

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.7151. Min Act: -0.0000

Data Index: 1640440 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.8212. Min Act: -0.0000

Data Index: 1461966 (Python Code)

Max Activating Token Index: 117

Text #10

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.7230. Min Act: -0.0000

Data Index: 1645877 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.6159. Min Act: -0.0001

Data Index: 1487277 (Python Code)

Max Activating Token Index: 28

Text #12

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5300. Min Act: -0.0001

Data Index: 1618597 (Python Code)

Max Activating Token Index: 370

Text #13

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4991. Min Act: -0.0000

Data Index: 1459238 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5510. Min Act: -0.0000

Data Index: 1637772 (Python Code)

Max Activating Token Index: 675

Text #15

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.7529. Min Act: -0.0000

Data Index: 1391345 (Python Code)

Max Activating Token Index: 831

Text #16

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4400. Min Act: -0.0000

Data Index: 1618389 (Python Code)

Max Activating Token Index: 646

Text #17

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.3996. Min Act: -0.0000

Data Index: 1528329 (Python Code)

Max Activating Token Index: 612

Text #18

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5596. Min Act: -0.0000

Data Index: 1393365 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4661. Min Act: -0.0001

Data Index: 1612230 (Python Code)

Max Activating Token Index: 21