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

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

Neuron 2122 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.1028. Min Act: -0.0002

Data Index: 603482 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1337136 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0948. Min Act: -0.0002

Data Index: 644482 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1144418 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1006910 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0918. Min Act: -0.0002

Data Index: 123839 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0895. Min Act: -0.0002

Data Index: 109079 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1064018 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0853. Min Act: -0.0002

Data Index: 995273 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1333341 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0864. Min Act: -0.0002

Data Index: 949923 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0857. Min Act: -0.0002

Data Index: 474957 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0777. Min Act: -0.0002

Data Index: 117087 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0853. Min Act: -0.0002

Data Index: 73994 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1043205 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0849. Min Act: -0.0002

Data Index: 398378 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0863. Min Act: -0.0002

Data Index: 161382 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0832. Min Act: -0.0002

Data Index: 63095 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0796. Min Act: -0.0002

Data Index: 804435 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0811. Min Act: -0.0002

Data Index: 17050 (C4 (Web Text))

Max Activating Token Index: 39