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

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

Neuron 260 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.6196. Min Act: -0.0000

Data Index: 504058 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5328. Min Act: -0.0000

Data Index: 831560 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5040. Min Act: -0.0000

Data Index: 225157 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4951. Min Act: -0.0000

Data Index: 985862 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5206. Min Act: -0.0001

Data Index: 1152071 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1056656 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4920. Min Act: -0.0001

Data Index: 576742 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4439. Min Act: -0.0000

Data Index: 643445 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4522. Min Act: -0.0001

Data Index: 457766 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4690. Min Act: -0.0000

Data Index: 165150 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1156308 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4305. Min Act: -0.0001

Data Index: 530770 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4554. Min Act: -0.0000

Data Index: 73884 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4851. Min Act: -0.0000

Data Index: 278638 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4966. Min Act: -0.0000

Data Index: 283286 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4865. Min Act: -0.0000

Data Index: 890208 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4233. Min Act: -0.0000

Data Index: 209300 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4458. Min Act: -0.0001

Data Index: 63645 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4413. Min Act: -0.0000

Data Index: 246241 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4430. Min Act: -0.0000

Data Index: 892447 (C4 (Web Text))

Max Activating Token Index: 718