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

Dataset: The Pile

Neuron 3118 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: 0.7700. Min Range: -0.7700

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1700949 (The Pile)

Max Activating Token Index: 634

Text #1

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1028317 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1188133 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1175395 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6576. Min Act: -0.0000

Data Index: 402469 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1218875 (The Pile)

Max Activating Token Index: 839

Text #6

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6408. Min Act: -0.0000

Data Index: 717320 (The Pile)

Max Activating Token Index: 398

Text #7

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1251834 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1664367 (The Pile)

Max Activating Token Index: 320

Text #9

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6353. Min Act: -0.0000

Data Index: 385749 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1402790 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1984665 (The Pile)

Max Activating Token Index: 720

Text #12

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1784020 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5976. Min Act: -0.0000

Data Index: 222652 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1170711 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1524296 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6364. Min Act: -0.0000

Data Index: 338279 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1994085 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1103152 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1887021 (The Pile)

Max Activating Token Index: 138