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

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

Neuron 2279 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1417448 (Python Code)

Max Activating Token Index: 273

Text #1

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1558864 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1563146 (Python Code)

Max Activating Token Index: 413

Text #3

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1435437 (Python Code)

Max Activating Token Index: 451

Text #4

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1556255 (Python Code)

Max Activating Token Index: 102

Text #5

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1567235 (Python Code)

Max Activating Token Index: 91

Text #6

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3615. Min Act: -0.0000

Data Index: 497986 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3435. Min Act: -0.0000

Data Index: 253611 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3270. Min Act: -0.0000

Data Index: 408903 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1098604 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3464. Min Act: -0.0000

Data Index: 995067 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3139. Min Act: -0.0000

Data Index: 932188 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2858. Min Act: -0.0000

Data Index: 914770 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2506. Min Act: -0.0000

Data Index: 661402 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1413874 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1053291 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2165. Min Act: -0.0000

Data Index: 775987 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2197. Min Act: -0.0000

Data Index: 473214 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2027. Min Act: -0.0000

Data Index: 746378 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1653409 (Python Code)

Max Activating Token Index: 894