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

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

Neuron 2370 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: 0.3798. Min Range: -0.3798

Max Act: 0.3798. Min Act: -0.0000

Data Index: 143489 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2929. Min Act: -0.0000

Data Index: 546216 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3000. Min Act: -0.0000

Data Index: 162634 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2915. Min Act: -0.0000

Data Index: 511769 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2778. Min Act: -0.0000

Data Index: 758889 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1337563 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2613. Min Act: -0.0000

Data Index: 23557 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2681. Min Act: -0.0001

Data Index: 1550345 (Python Code)

Max Activating Token Index: 179

Text #8

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1111719 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2571. Min Act: -0.0001

Data Index: 1512563 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2595. Min Act: -0.0001

Data Index: 1490976 (Python Code)

Max Activating Token Index: 394

Text #11

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2528. Min Act: -0.0001

Data Index: 1505165 (Python Code)

Max Activating Token Index: 169

Text #12

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1423184 (Python Code)

Max Activating Token Index: 743

Text #13

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2442. Min Act: -0.0001

Data Index: 1400131 (Python Code)

Max Activating Token Index: 185

Text #14

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2579. Min Act: -0.0001

Data Index: 1613468 (Python Code)

Max Activating Token Index: 165

Text #15

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2483. Min Act: -0.0000

Data Index: 855991 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2472. Min Act: -0.0001

Data Index: 1372523 (Python Code)

Max Activating Token Index: 346

Text #17

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2315. Min Act: -0.0000

Data Index: 324572 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2388. Min Act: -0.0001

Data Index: 1433228 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1522633 (Python Code)

Max Activating Token Index: 183