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

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

Neuron 3580 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1257945 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1011. Min Act: -0.0002

Data Index: 578709 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1411726 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0979. Min Act: -0.0002

Data Index: 568569 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1062933 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1571927 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1392191 (Python Code)

Max Activating Token Index: 44

Text #7

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0943. Min Act: -0.0002

Data Index: 549310 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1550298 (Python Code)

Max Activating Token Index: 120

Text #9

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0933. Min Act: -0.0002

Data Index: 458553 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1433095 (Python Code)

Max Activating Token Index: 115

Text #11

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1276205 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1599133 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1476726 (Python Code)

Max Activating Token Index: 176

Text #14

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1251910 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0872. Min Act: -0.0002

Data Index: 832433 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1183420 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1570040 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0863. Min Act: -0.0002

Data Index: 642297 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0857. Min Act: -0.0003

Data Index: 815918 (C4 (Web Text))

Max Activating Token Index: 358