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

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

Neuron 2596 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: 0.1163. Min Range: -0.1163

Max Act: 0.1163. Min Act: -0.0003

Data Index: 431326 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1337408 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0924. Min Act: -0.0003

Data Index: 302244 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0908. Min Act: -0.0002

Data Index: 281841 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0885. Min Act: -0.0003

Data Index: 304701 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0881. Min Act: -0.0003

Data Index: 1163200 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0880. Min Act: -0.0002

Data Index: 657212 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0848. Min Act: -0.0003

Data Index: 38966 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0863. Min Act: -0.0002

Data Index: 173557 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0858. Min Act: -0.0002

Data Index: 900102 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0825. Min Act: -0.0002

Data Index: 755410 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1346451 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0827. Min Act: -0.0002

Data Index: 454847 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0808. Min Act: -0.0003

Data Index: 451665 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0822. Min Act: -0.0002

Data Index: 550305 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0800. Min Act: -0.0002

Data Index: 332618 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0839. Min Act: -0.0002

Data Index: 426882 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0805. Min Act: -0.0002

Data Index: 453627 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0817. Min Act: -0.0002

Data Index: 830725 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1312717 (C4 (Web Text))

Max Activating Token Index: 192