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

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

Neuron 2478 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3942. Min Range: -4.3942

Max Act: 4.2597. Min Act: -0.0000

Data Index: 1417829 (Python Code)

Max Activating Token Index: 694

Text #1

Max Range: 4.3942. Min Range: -4.3942

Max Act: 4.3942. Min Act: -0.0000

Data Index: 1400645 (Python Code)

Max Activating Token Index: 827

Text #2

Max Range: 4.3942. Min Range: -4.3942

Max Act: 4.0649. Min Act: -0.0000

Data Index: 1641291 (Python Code)

Max Activating Token Index: 653

Text #3

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.8601. Min Act: -0.0000

Data Index: 1404646 (Python Code)

Max Activating Token Index: 853

Text #4

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.6553. Min Act: -0.0000

Data Index: 1580576 (Python Code)

Max Activating Token Index: 504

Text #5

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.6966. Min Act: -0.0000

Data Index: 1577540 (Python Code)

Max Activating Token Index: 993

Text #6

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.5107. Min Act: -0.0000

Data Index: 1590668 (Python Code)

Max Activating Token Index: 200

Text #7

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.2565. Min Act: -0.0000

Data Index: 1594846 (Python Code)

Max Activating Token Index: 816

Text #8

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.3303. Min Act: -0.0000

Data Index: 1411970 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.4680. Min Act: -0.0000

Data Index: 1520098 (Python Code)

Max Activating Token Index: 1021

Text #10

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.3026. Min Act: -0.0000

Data Index: 1543736 (Python Code)

Max Activating Token Index: 573

Text #11

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.3116. Min Act: -0.0000

Data Index: 1408228 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.1696. Min Act: -0.0000

Data Index: 1509639 (Python Code)

Max Activating Token Index: 212

Text #13

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.2714. Min Act: -0.0000

Data Index: 1497021 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.1690. Min Act: -0.0000

Data Index: 1363075 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 4.3942. Min Range: -4.3942

Max Act: 3.1713. Min Act: -0.0000

Data Index: 1516002 (Python Code)

Max Activating Token Index: 630

Text #16

Max Range: 4.3942. Min Range: -4.3942

Max Act: 2.9047. Min Act: -0.0000

Data Index: 1597041 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 4.3942. Min Range: -4.3942

Max Act: 2.7523. Min Act: -0.0000

Data Index: 1626966 (Python Code)

Max Activating Token Index: 997

Text #18

Max Range: 4.3942. Min Range: -4.3942

Max Act: 2.7605. Min Act: -0.0000

Data Index: 1493734 (Python Code)

Max Activating Token Index: 211

Text #19

Max Range: 4.3942. Min Range: -4.3942

Max Act: 2.9799. Min Act: -0.0000

Data Index: 1453102 (Python Code)

Max Activating Token Index: 34