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

Dataset: The Pile

Neuron 5074 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: 1.0802. Min Range: -1.0802

Max Act: 1.0358. Min Act: -0.0000

Data Index: 1956948 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1808561 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1457654 (The Pile)

Max Activating Token Index: 581

Text #3

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1847939 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1248634 (The Pile)

Max Activating Token Index: 633

Text #5

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1022719 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9868. Min Act: -0.0000

Data Index: 1050453 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9072. Min Act: -0.0000

Data Index: 908050 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8568. Min Act: -0.0000

Data Index: 513410 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9248. Min Act: -0.0000

Data Index: 584572 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1688682 (The Pile)

Max Activating Token Index: 575

Text #11

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8519. Min Act: -0.0000

Data Index: 750525 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1368085 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8552. Min Act: -0.0000

Data Index: 862488 (The Pile)

Max Activating Token Index: 718

Text #14

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1071709 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1723197 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8489. Min Act: -0.0000

Data Index: 162199 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1914918 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1911562 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8036. Min Act: -0.0000

Data Index: 487271 (The Pile)

Max Activating Token Index: 433