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

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

Neuron 523 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2390. Min Act: -0.0001

Data Index: 535535 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2205. Min Act: -0.0001

Data Index: 68724 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2163. Min Act: -0.0000

Data Index: 747223 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2057. Min Act: -0.0000

Data Index: 913382 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1783. Min Act: -0.0000

Data Index: 450677 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1891. Min Act: -0.0000

Data Index: 420236 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1007546 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1844. Min Act: -0.0000

Data Index: 373945 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1736. Min Act: -0.0001

Data Index: 100410 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1118502 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1734. Min Act: -0.0001

Data Index: 1177230 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1755. Min Act: -0.0000

Data Index: 677542 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1795. Min Act: -0.0000

Data Index: 404333 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1725. Min Act: -0.0000

Data Index: 223003 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1610. Min Act: -0.0001

Data Index: 804089 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1799. Min Act: -0.0000

Data Index: 853597 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1662. Min Act: -0.0000

Data Index: 415280 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1586. Min Act: -0.0000

Data Index: 403048 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1643. Min Act: -0.0000

Data Index: 144550 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1566. Min Act: -0.0001

Data Index: 780907 (C4 (Web Text))

Max Activating Token Index: 242