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

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

Neuron 4435 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3870. Min Act: -0.0000

Data Index: 283549 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1057718 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.7815. Min Act: -0.0000

Data Index: 946550 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.7253. Min Act: -0.0000

Data Index: 863825 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1525978 (Python Code)

Max Activating Token Index: 586

Text #5

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.7609. Min Act: -0.0000

Data Index: 272358 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6989. Min Act: -0.0000

Data Index: 406069 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6978. Min Act: -0.0000

Data Index: 769719 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1074935 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6687. Min Act: -0.0000

Data Index: 4822 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1126274 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6661. Min Act: -0.0000

Data Index: 839034 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1287993 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1138543 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1187667 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6410. Min Act: -0.0000

Data Index: 260167 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6712. Min Act: -0.0000

Data Index: 96647 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6442. Min Act: 0.0002

Data Index: 757265 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6646. Min Act: -0.0000

Data Index: 876256 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.3870. Min Range: -1.3870

Max Act: 0.6291. Min Act: -0.0000

Data Index: 355777 (C4 (Web Text))

Max Activating Token Index: 703