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

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

Neuron 776 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3600. Min Range: -2.3600

Max Act: 2.1661. Min Act: -0.0001

Data Index: 1454493 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 2.3600. Min Range: -2.3600

Max Act: 2.3600. Min Act: -0.0000

Data Index: 1383984 (Python Code)

Max Activating Token Index: 199

Text #2

Max Range: 2.3600. Min Range: -2.3600

Max Act: 2.0466. Min Act: -0.0000

Data Index: 1581412 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 2.3600. Min Range: -2.3600

Max Act: 2.1459. Min Act: -0.0000

Data Index: 1572968 (Python Code)

Max Activating Token Index: 414

Text #4

Max Range: 2.3600. Min Range: -2.3600

Max Act: 2.0880. Min Act: -0.0001

Data Index: 1652612 (Python Code)

Max Activating Token Index: 118

Text #5

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.9874. Min Act: -0.0000

Data Index: 1652403 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.9691. Min Act: -0.0001

Data Index: 1571562 (Python Code)

Max Activating Token Index: 79

Text #7

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.9658. Min Act: -0.0000

Data Index: 1580660 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.9578. Min Act: -0.0000

Data Index: 1517092 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.9285. Min Act: -0.0000

Data Index: 1446517 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 2.3600. Min Range: -2.3600

Max Act: 2.0279. Min Act: -0.0000

Data Index: 1493644 (Python Code)

Max Activating Token Index: 148

Text #11

Max Range: 2.3600. Min Range: -2.3600

Max Act: 2.0231. Min Act: -0.0000

Data Index: 1489849 (Python Code)

Max Activating Token Index: 759

Text #12

Max Range: 2.3600. Min Range: -2.3600

Max Act: 2.0243. Min Act: -0.0000

Data Index: 1531474 (Python Code)

Max Activating Token Index: 409

Text #13

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.9037. Min Act: -0.0000

Data Index: 1586974 (Python Code)

Max Activating Token Index: 159

Text #14

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.9180. Min Act: -0.0000

Data Index: 1364210 (Python Code)

Max Activating Token Index: 139

Text #15

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.7946. Min Act: -0.0000

Data Index: 1648388 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.9989. Min Act: -0.0001

Data Index: 1646636 (Python Code)

Max Activating Token Index: 194

Text #17

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.7835. Min Act: -0.0000

Data Index: 1508939 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.8729. Min Act: -0.0000

Data Index: 1509037 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 2.3600. Min Range: -2.3600

Max Act: 1.9672. Min Act: -0.0001

Data Index: 1596615 (Python Code)

Max Activating Token Index: 832