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

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

Neuron 2400 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: 0.6734. Min Range: -0.6734

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1284854 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1023028 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.6314. Min Act: -0.0000

Data Index: 613013 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.6210. Min Act: -0.0000

Data Index: 210554 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5833. Min Act: -0.0000

Data Index: 292426 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.6167. Min Act: -0.0000

Data Index: 629300 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.6042. Min Act: -0.0000

Data Index: 173102 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5857. Min Act: -0.0000

Data Index: 107815 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5460. Min Act: -0.0000

Data Index: 300750 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1058342 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5130. Min Act: -0.0000

Data Index: 715669 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1105717 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5170. Min Act: -0.0000

Data Index: 214161 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4826. Min Act: -0.0000

Data Index: 645186 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5219. Min Act: -0.0000

Data Index: 320332 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4971. Min Act: -0.0000

Data Index: 443171 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1112110 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4906. Min Act: -0.0000

Data Index: 108623 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5199. Min Act: -0.0000

Data Index: 717455 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5253. Min Act: -0.0000

Data Index: 258743 (C4 (Web Text))

Max Activating Token Index: 187