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

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

Neuron 5026 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.4301. Min Act: -0.0000

Data Index: 364489 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.3760. Min Act: -0.0000

Data Index: 777852 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.5781. Min Act: -0.0000

Data Index: 613406 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.4394. Min Act: -0.0000

Data Index: 1035881 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.4232. Min Act: -0.0000

Data Index: 1233297 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.3351. Min Act: -0.0000

Data Index: 1349397 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.3394. Min Act: -0.0000

Data Index: 418951 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.3083. Min Act: -0.0000

Data Index: 891542 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.4205. Min Act: -0.0000

Data Index: 332835 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.2444. Min Act: -0.0000

Data Index: 825886 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.2131. Min Act: -0.0000

Data Index: 1262072 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.2991. Min Act: -0.0000

Data Index: 528551 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.2646. Min Act: -0.0000

Data Index: 452670 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 2.5781. Min Range: -2.5781

Max Act: 1.9314. Min Act: -0.0000

Data Index: 718765 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.0220. Min Act: -0.0000

Data Index: 97105 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.1001. Min Act: -0.0000

Data Index: 449150 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.1945. Min Act: -0.0000

Data Index: 1036345 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.0624. Min Act: -0.0000

Data Index: 1322852 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 2.5781. Min Range: -2.5781

Max Act: 1.9384. Min Act: -0.0000

Data Index: 366519 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 2.5781. Min Range: -2.5781

Max Act: 2.0212. Min Act: -0.0000

Data Index: 1264017 (C4 (Web Text))

Max Activating Token Index: 56