Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3608 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.6364. Min Act: -0.0000

Data Index: 594234 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1282582 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.6520. Min Act: -0.0000

Data Index: 471326 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1260398 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.6476. Min Act: -0.0000

Data Index: 19786 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1105601 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5786. Min Act: -0.0000

Data Index: 743798 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5907. Min Act: -0.0000

Data Index: 994328 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.6022. Min Act: -0.0000

Data Index: 483685 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5919. Min Act: -0.0000

Data Index: 23269 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1186459 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.6179. Min Act: -0.0000

Data Index: 399232 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1282397 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1000655 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5989. Min Act: -0.0000

Data Index: 941938 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5804. Min Act: -0.0000

Data Index: 194523 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5889. Min Act: -0.0000

Data Index: 506499 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1351887 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5971. Min Act: -0.0000

Data Index: 874096 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5404. Min Act: -0.0000

Data Index: 98588 (C4 (Web Text))

Max Activating Token Index: 546