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

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

Neuron 3074 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: 1.2061. Min Range: -1.2061

Max Act: 1.2061. Min Act: -0.0002

Data Index: 380436 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.1516. Min Act: -0.0002

Data Index: 1299303 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.1144. Min Act: -0.0002

Data Index: 26019 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.1283. Min Act: -0.0002

Data Index: 139970 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0951. Min Act: -0.0002

Data Index: 106464 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.1116. Min Act: -0.0002

Data Index: 255785 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0857. Min Act: -0.0002

Data Index: 1085790 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0929. Min Act: -0.0002

Data Index: 112968 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0806. Min Act: -0.0002

Data Index: 962077 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0922. Min Act: -0.0002

Data Index: 991993 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0758. Min Act: -0.0002

Data Index: 618773 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0918. Min Act: -0.0002

Data Index: 577067 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0866. Min Act: -0.0002

Data Index: 628305 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0832. Min Act: -0.0002

Data Index: 457669 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0789. Min Act: -0.0002

Data Index: 1077573 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0755. Min Act: -0.0002

Data Index: 1045109 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0483. Min Act: -0.0002

Data Index: 2007 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0535. Min Act: -0.0002

Data Index: 666937 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0697. Min Act: -0.0002

Data Index: 843658 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.2061. Min Range: -1.2061

Max Act: 1.0644. Min Act: -0.0002

Data Index: 352174 (C4 (Web Text))

Max Activating Token Index: 58