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

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

Neuron 3433 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1262057 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5545. Min Act: -0.0001

Data Index: 1448857 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4471. Min Act: -0.0001

Data Index: 1589386 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4262. Min Act: -0.0001

Data Index: 1402145 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4338. Min Act: -0.0001

Data Index: 1647183 (Python Code)

Max Activating Token Index: 158

Text #5

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4261. Min Act: -0.0001

Data Index: 1532995 (Python Code)

Max Activating Token Index: 759

Text #6

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4452. Min Act: -0.0001

Data Index: 1628545 (Python Code)

Max Activating Token Index: 786

Text #7

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3976. Min Act: -0.0001

Data Index: 1604833 (Python Code)

Max Activating Token Index: 398

Text #8

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4419. Min Act: -0.0001

Data Index: 1406712 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4056. Min Act: -0.0000

Data Index: 455501 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3922. Min Act: -0.0001

Data Index: 1616273 (Python Code)

Max Activating Token Index: 154

Text #11

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4041. Min Act: -0.0001

Data Index: 1623160 (Python Code)

Max Activating Token Index: 865

Text #12

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3935. Min Act: -0.0000

Data Index: 546181 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4147. Min Act: -0.0001

Data Index: 1368094 (Python Code)

Max Activating Token Index: 242

Text #14

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1520066 (Python Code)

Max Activating Token Index: 990

Text #15

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3863. Min Act: -0.0001

Data Index: 1398217 (Python Code)

Max Activating Token Index: 698

Text #16

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3963. Min Act: -0.0001

Data Index: 1496264 (Python Code)

Max Activating Token Index: 206

Text #17

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3927. Min Act: -0.0001

Data Index: 1488506 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3891. Min Act: -0.0001

Data Index: 1498465 (Python Code)

Max Activating Token Index: 339

Text #19

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1559882 (Python Code)

Max Activating Token Index: 1021