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

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

Neuron 561 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.3363. Min Act: -0.0000

Data Index: 727620 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.2851. Min Act: -0.0000

Data Index: 117785 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.2053. Min Act: -0.0000

Data Index: 617652 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.2555. Min Act: -0.0000

Data Index: 966005 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.2034. Min Act: -0.0000

Data Index: 974045 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.0769. Min Act: -0.0000

Data Index: 428410 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.0745. Min Act: -0.0000

Data Index: 727916 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.0506. Min Act: -0.0000

Data Index: 1207719 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.1402. Min Act: -0.0000

Data Index: 542134 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.0899. Min Act: -0.0000

Data Index: 669957 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.1581. Min Act: -0.0000

Data Index: 853531 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 2.3363. Min Range: -2.3363

Max Act: 1.9763. Min Act: -0.0000

Data Index: 1001556 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.1770. Min Act: -0.0000

Data Index: 856565 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.0913. Min Act: -0.0000

Data Index: 214238 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.0740. Min Act: -0.0000

Data Index: 1328533 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.0870. Min Act: -0.0000

Data Index: 368121 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.0697. Min Act: -0.0000

Data Index: 941053 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 2.3363. Min Range: -2.3363

Max Act: 1.9676. Min Act: -0.0000

Data Index: 291232 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 2.3363. Min Range: -2.3363

Max Act: 1.9445. Min Act: -0.0000

Data Index: 1140207 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 2.3363. Min Range: -2.3363

Max Act: 2.0553. Min Act: -0.0000

Data Index: 133593 (C4 (Web Text))

Max Activating Token Index: 198