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

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

Neuron 678 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2093. Min Range: -3.2093

Max Act: 3.2093. Min Act: -0.0000

Data Index: 1211642 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.8793. Min Act: -0.0000

Data Index: 216698 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.7271. Min Act: -0.0001

Data Index: 286957 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.6624. Min Act: -0.0000

Data Index: 711116 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.1871. Min Act: -0.0000

Data Index: 1039460 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.5229. Min Act: -0.0001

Data Index: 1043124 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.3163. Min Act: -0.0000

Data Index: 476219 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.4723. Min Act: -0.0001

Data Index: 878157 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.3286. Min Act: -0.0000

Data Index: 592422 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.2995. Min Act: -0.0000

Data Index: 618900 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.2296. Min Act: -0.0001

Data Index: 1223492 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.1630. Min Act: -0.0000

Data Index: 147021 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.2199. Min Act: -0.0001

Data Index: 1335720 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.2544. Min Act: -0.0001

Data Index: 408016 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.3627. Min Act: -0.0000

Data Index: 878632 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.0024. Min Act: -0.0000

Data Index: 594984 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.3226. Min Act: -0.0001

Data Index: 260391 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.3011. Min Act: -0.0001

Data Index: 434511 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 3.2093. Min Range: -3.2093

Max Act: 1.9529. Min Act: -0.0001

Data Index: 395082 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 3.2093. Min Range: -3.2093

Max Act: 2.0572. Min Act: -0.0000

Data Index: 68628 (C4 (Web Text))

Max Activating Token Index: 284