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

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

Neuron 1394 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0713. Min Range: -2.0713

Max Act: 2.0713. Min Act: -0.0000

Data Index: 1550642 (Python Code)

Max Activating Token Index: 474

Text #1

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.9421. Min Act: -0.0000

Data Index: 1460883 (Python Code)

Max Activating Token Index: 828

Text #2

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.8192. Min Act: -0.0000

Data Index: 944261 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.7523. Min Act: -0.0000

Data Index: 567702 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.6576. Min Act: -0.0000

Data Index: 1468886 (Python Code)

Max Activating Token Index: 129

Text #5

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.7192. Min Act: -0.0000

Data Index: 516858 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.5830. Min Act: -0.0001

Data Index: 734721 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.6731. Min Act: -0.0000

Data Index: 587220 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.7592. Min Act: -0.0001

Data Index: 1625662 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.5456. Min Act: -0.0000

Data Index: 594548 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.5439. Min Act: -0.0000

Data Index: 164096 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.4858. Min Act: -0.0001

Data Index: 1024212 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.5926. Min Act: -0.0000

Data Index: 555938 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.5710. Min Act: -0.0001

Data Index: 668658 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.5061. Min Act: -0.0000

Data Index: 580487 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.4285. Min Act: -0.0000

Data Index: 1225885 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.6289. Min Act: -0.0000

Data Index: 48007 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.5005. Min Act: -0.0000

Data Index: 368289 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.5057. Min Act: -0.0000

Data Index: 450736 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 2.0713. Min Range: -2.0713

Max Act: 1.5105. Min Act: -0.0001

Data Index: 1317650 (C4 (Web Text))

Max Activating Token Index: 128