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

Dataset: The Pile

Neuron 2100 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1406054 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1227301 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0478. Min Act: -0.0000

Data Index: 1544206 (The Pile)

Max Activating Token Index: 79

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0475. Min Act: -0.0000

Data Index: 1567474 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0468. Min Act: 0.0000

Data Index: 1712977 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0467. Min Act: -0.0000

Data Index: 314076 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0465. Min Act: -0.0000

Data Index: 632668 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0462. Min Act: -0.0000

Data Index: 57844 (The Pile)

Max Activating Token Index: 607

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0445. Min Act: -0.0000

Data Index: 805203 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1988681 (The Pile)

Max Activating Token Index: 824

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0460. Min Act: -0.0000

Data Index: 545192 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0456. Min Act: -0.0000

Data Index: 571471 (The Pile)

Max Activating Token Index: 824

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0450. Min Act: -0.0000

Data Index: 1409424 (The Pile)

Max Activating Token Index: 3

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0446. Min Act: -0.0000

Data Index: 769680 (The Pile)

Max Activating Token Index: 917

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0445. Min Act: -0.0000

Data Index: 567772 (The Pile)

Max Activating Token Index: 12

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0443. Min Act: -0.0000

Data Index: 855628 (The Pile)

Max Activating Token Index: 91

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0442. Min Act: -0.0000

Data Index: 1302337 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1005767 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1747810 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0434. Min Act: -0.0000

Data Index: 861644 (The Pile)

Max Activating Token Index: 512