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

Dataset: The Pile

Neuron 4109 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: 0.3402. Min Range: -0.3402

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1211346 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3113. Min Act: -0.0000

Data Index: 633828 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1463328 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3025. Min Act: -0.0000

Data Index: 344739 (The Pile)

Max Activating Token Index: 31

Text #4

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2727. Min Act: -0.0000

Data Index: 822377 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1207573 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1621261 (The Pile)

Max Activating Token Index: 632

Text #7

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2755. Min Act: -0.0000

Data Index: 131744 (The Pile)

Max Activating Token Index: 414

Text #8

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1161133 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2718. Min Act: -0.0000

Data Index: 447612 (The Pile)

Max Activating Token Index: 55

Text #10

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2743. Min Act: -0.0000

Data Index: 154037 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1874923 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1929184 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2417. Min Act: -0.0000

Data Index: 767577 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2459. Min Act: -0.0000

Data Index: 485311 (The Pile)

Max Activating Token Index: 919

Text #15

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2461. Min Act: -0.0000

Data Index: 624912 (The Pile)

Max Activating Token Index: 61

Text #16

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1065672 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1238019 (The Pile)

Max Activating Token Index: 588

Text #18

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1508087 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2298. Min Act: -0.0000

Data Index: 594220 (The Pile)

Max Activating Token Index: 79