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

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

Neuron 4005 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.7234. Min Act: -0.0002

Data Index: 766207 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.6485. Min Act: -0.0002

Data Index: 167609 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.5822. Min Act: -0.0002

Data Index: 353259 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.6453. Min Act: -0.0002

Data Index: 975440 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.6424. Min Act: -0.0002

Data Index: 1074713 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.5989. Min Act: -0.0002

Data Index: 246668 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.3839. Min Act: -0.0002

Data Index: 1068416 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.5261. Min Act: -0.0002

Data Index: 946622 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.5432. Min Act: -0.0002

Data Index: 639333 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.4740. Min Act: -0.0002

Data Index: 1027113 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.5043. Min Act: -0.0002

Data Index: 59716 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.4111. Min Act: -0.0002

Data Index: 276275 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.4720. Min Act: -0.0002

Data Index: 196191 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.5013. Min Act: -0.0002

Data Index: 493879 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.4544. Min Act: -0.0002

Data Index: 924935 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.4456. Min Act: -0.0002

Data Index: 20978 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.3435. Min Act: -0.0002

Data Index: 244855 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.3711. Min Act: -0.0002

Data Index: 813819 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.3334. Min Act: -0.0002

Data Index: 837080 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 1.7234. Min Range: -1.7234

Max Act: 1.2899. Min Act: -0.0002

Data Index: 240183 (C4 (Web Text))

Max Activating Token Index: 312