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

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

Neuron 1582 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1497043 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2951. Min Act: -0.0001

Data Index: 712349 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2798. Min Act: -0.0000

Data Index: 81020 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2706. Min Act: -0.0000

Data Index: 668499 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2752. Min Act: -0.0000

Data Index: 136861 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1317683 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1298325 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2567. Min Act: -0.0000

Data Index: 420084 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2561. Min Act: -0.0000

Data Index: 202682 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1325531 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1196272 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1184196 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2509. Min Act: -0.0000

Data Index: 417345 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2670. Min Act: -0.0000

Data Index: 39597 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2479. Min Act: -0.0000

Data Index: 508661 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2595. Min Act: -0.0000

Data Index: 560982 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2598. Min Act: -0.0000

Data Index: 222703 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1402547 (Python Code)

Max Activating Token Index: 632

Text #18

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1634214 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1242166 (C4 (Web Text))

Max Activating Token Index: 192