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

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

Neuron 2400 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1723. Min Range: -3.1723

Max Act: 3.1723. Min Act: -0.0000

Data Index: 116506 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.3339. Min Act: -0.0000

Data Index: 714318 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.6235. Min Act: -0.0000

Data Index: 1064147 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.4730. Min Act: -0.0000

Data Index: 1011162 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.6110. Min Act: -0.0000

Data Index: 500145 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.2560. Min Act: -0.0000

Data Index: 1323179 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.3050. Min Act: -0.0000

Data Index: 805102 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.4426. Min Act: -0.0000

Data Index: 1072664 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.1925. Min Act: -0.0000

Data Index: 686300 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 3.1723. Min Range: -3.1723

Max Act: 1.9556. Min Act: -0.0000

Data Index: 25288 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.0594. Min Act: -0.0000

Data Index: 240602 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.1611. Min Act: -0.0000

Data Index: 274614 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.0266. Min Act: -0.0000

Data Index: 689364 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.0082. Min Act: -0.0000

Data Index: 863377 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 3.1723. Min Range: -3.1723

Max Act: 1.9900. Min Act: -0.0000

Data Index: 1297286 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 3.1723. Min Range: -3.1723

Max Act: 2.0968. Min Act: -0.0000

Data Index: 370246 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 3.1723. Min Range: -3.1723

Max Act: 1.8768. Min Act: -0.0000

Data Index: 557612 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 3.1723. Min Range: -3.1723

Max Act: 1.9409. Min Act: -0.0000

Data Index: 866050 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 3.1723. Min Range: -3.1723

Max Act: 1.8859. Min Act: -0.0000

Data Index: 572549 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 3.1723. Min Range: -3.1723

Max Act: 1.9455. Min Act: -0.0000

Data Index: 654709 (C4 (Web Text))

Max Activating Token Index: 560