Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 854 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5575. Min Act: -0.0002

Data Index: 655812 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4761. Min Act: -0.0001

Data Index: 396826 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4561. Min Act: -0.0002

Data Index: 976817 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3982. Min Act: -0.0002

Data Index: 109695 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3292. Min Act: -0.0001

Data Index: 442882 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4007. Min Act: -0.0002

Data Index: 631332 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3362. Min Act: -0.0001

Data Index: 344427 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3387. Min Act: -0.0002

Data Index: 416308 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2736. Min Act: -0.0002

Data Index: 351269 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3363. Min Act: -0.0002

Data Index: 181039 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4074. Min Act: -0.0001

Data Index: 1300868 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2947. Min Act: -0.0001

Data Index: 526413 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3113. Min Act: -0.0002

Data Index: 392240 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2487. Min Act: -0.0002

Data Index: 207906 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2067. Min Act: -0.0002

Data Index: 394074 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1434. Min Act: -0.0002

Data Index: 1354633 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1579. Min Act: -0.0001

Data Index: 860298 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2290. Min Act: -0.0002

Data Index: 584990 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2265. Min Act: -0.0001

Data Index: 84813 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1968. Min Act: -0.0001

Data Index: 1259587 (C4 (Web Text))

Max Activating Token Index: 865