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

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

Neuron 2041 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: 0.4517. Min Range: -0.4517

Max Act: 0.4517. Min Act: -0.0000

Data Index: 33530 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.4179. Min Act: -0.0000

Data Index: 447033 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.3290. Min Act: -0.0000

Data Index: 449591 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.3099. Min Act: -0.0000

Data Index: 473573 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.3081. Min Act: -0.0000

Data Index: 215706 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2884. Min Act: -0.0000

Data Index: 461037 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2648. Min Act: -0.0000

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2655. Min Act: -0.0000

Data Index: 833342 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1359519 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1177169 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2535. Min Act: -0.0000

Data Index: 816956 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2323. Min Act: -0.0000

Data Index: 282940 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2270. Min Act: -0.0000

Data Index: 549547 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2301. Min Act: -0.0000

Data Index: 567618 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1077169 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1233283 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2463. Min Act: -0.0001

Data Index: 81784 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2250. Min Act: -0.0000

Data Index: 905640 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2007. Min Act: -0.0000

Data Index: 400991 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.4517. Min Range: -0.4517

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1061429 (C4 (Web Text))

Max Activating Token Index: 215