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

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

Neuron 5657 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.6221. Min Act: -0.0000

Data Index: 66560 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.5593. Min Act: -0.0000

Data Index: 433176 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.5327. Min Act: -0.0000

Data Index: 469198 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.5246. Min Act: -0.0000

Data Index: 1059607 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.6455. Min Act: -0.0000

Data Index: 80124 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.2527. Min Act: -0.0000

Data Index: 1263584 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.3522. Min Act: -0.0000

Data Index: 144354 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.4540. Min Act: -0.0000

Data Index: 348737 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.1751. Min Act: -0.0000

Data Index: 940240 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1534120 (Python Code)

Max Activating Token Index: 548

Text #10

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.2197. Min Act: -0.0000

Data Index: 1120766 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.2400. Min Act: -0.0000

Data Index: 503775 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.2773. Min Act: -0.0000

Data Index: 1108599 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.0288. Min Act: -0.0000

Data Index: 1474121 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.0112. Min Act: -0.0000

Data Index: 362402 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.2529. Min Act: -0.0000

Data Index: 186089 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.0778. Min Act: -0.0000

Data Index: 649543 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 2.6455. Min Range: -2.6455

Max Act: 1.9628. Min Act: -0.0000

Data Index: 20947 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.0599. Min Act: -0.0000

Data Index: 459982 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 2.6455. Min Range: -2.6455

Max Act: 2.0228. Min Act: -0.0000

Data Index: 97881 (C4 (Web Text))

Max Activating Token Index: 273