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

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

Neuron 3466 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3497. Min Act: -0.0001

Data Index: 148118 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3190. Min Act: -0.0001

Data Index: 777459 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2748. Min Act: -0.0000

Data Index: 549234 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2752. Min Act: -0.0001

Data Index: 470126 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2525. Min Act: -0.0001

Data Index: 219701 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2783. Min Act: -0.0000

Data Index: 720525 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2494. Min Act: -0.0001

Data Index: 429239 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2549. Min Act: -0.0000

Data Index: 249722 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1077096 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1326770 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2571. Min Act: -0.0000

Data Index: 178462 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2593. Min Act: -0.0001

Data Index: 869087 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2495. Min Act: -0.0000

Data Index: 822491 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2598. Min Act: -0.0001

Data Index: 480820 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2655. Min Act: -0.0000

Data Index: 205310 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2432. Min Act: -0.0001

Data Index: 784090 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2463. Min Act: -0.0000

Data Index: 252642 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2595. Min Act: -0.0000

Data Index: 148831 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2493. Min Act: -0.0000

Data Index: 508454 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2423. Min Act: -0.0001

Data Index: 263119 (C4 (Web Text))

Max Activating Token Index: 766