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

Dataset: The Pile

Neuron 3672 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.2573. Min Act: -0.0000

Data Index: 1708527 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.4485. Min Act: -0.0000

Data Index: 1171691 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1158003 (The Pile)

Max Activating Token Index: 64

Text #3

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.0363. Min Act: -0.0000

Data Index: 538305 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.0945. Min Act: 0.0000

Data Index: 1856444 (The Pile)

Max Activating Token Index: 866

Text #5

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9442. Min Act: -0.0000

Data Index: 502188 (The Pile)

Max Activating Token Index: 768

Text #6

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8334. Min Act: -0.0000

Data Index: 984061 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9888. Min Act: -0.0000

Data Index: 709767 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1732174 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8225. Min Act: -0.0000

Data Index: 781799 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1503601 (The Pile)

Max Activating Token Index: 70

Text #11

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9760. Min Act: -0.0000

Data Index: 395771 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8777. Min Act: -0.0000

Data Index: 21092 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.7686. Min Act: -0.0000

Data Index: 20090 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1792144 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1624053 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8821. Min Act: -0.0000

Data Index: 192153 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1827578 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1059254 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1153940 (The Pile)

Max Activating Token Index: 190