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

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

Neuron 4634 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3276. Min Act: -0.0000

Data Index: 476800 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1222103 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3598. Min Act: -0.0000

Data Index: 384347 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1265542 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3025. Min Act: -0.0000

Data Index: 903559 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3138. Min Act: -0.0000

Data Index: 543387 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3112. Min Act: -0.0000

Data Index: 371555 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3228. Min Act: -0.0000

Data Index: 320460 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3203. Min Act: -0.0000

Data Index: 484421 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2885. Min Act: -0.0000

Data Index: 389753 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2985. Min Act: -0.0000

Data Index: 512850 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1325349 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2979. Min Act: -0.0000

Data Index: 812123 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2694. Min Act: -0.0000

Data Index: 761867 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3066. Min Act: -0.0000

Data Index: 276742 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2833. Min Act: -0.0000

Data Index: 32637 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2850. Min Act: -0.0000

Data Index: 495766 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2874. Min Act: -0.0000

Data Index: 349390 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1318366 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2791. Min Act: -0.0000

Data Index: 515509 (C4 (Web Text))

Max Activating Token Index: 178