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

Dataset: The Pile

Neuron 1330 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1424644 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.8870. Min Act: -0.0000

Data Index: 534669 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1427170 (The Pile)

Max Activating Token Index: 996

Text #3

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1161797 (The Pile)

Max Activating Token Index: 299

Text #4

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.8191. Min Act: -0.0000

Data Index: 676174 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1252952 (The Pile)

Max Activating Token Index: 974

Text #6

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7855. Min Act: -0.0000

Data Index: 31579 (The Pile)

Max Activating Token Index: 813

Text #7

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1093578 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1550035 (The Pile)

Max Activating Token Index: 904

Text #9

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1304982 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1592423 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7588. Min Act: -0.0000

Data Index: 580223 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7634. Min Act: -0.0000

Data Index: 729238 (The Pile)

Max Activating Token Index: 217

Text #13

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1157334 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1145892 (The Pile)

Max Activating Token Index: 250

Text #15

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1427592 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1660286 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7384. Min Act: -0.0000

Data Index: 682805 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7173. Min Act: -0.0000

Data Index: 775687 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7308. Min Act: -0.0000

Data Index: 715958 (The Pile)

Max Activating Token Index: 13