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

Dataset: The Pile

Neuron 4970 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2855. Min Act: -0.0000

Data Index: 1212609 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1294996 (The Pile)

Max Activating Token Index: 86

Text #2

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2655. Min Act: -0.0000

Data Index: 314025 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2787. Min Act: -0.0000

Data Index: 236096 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2646. Min Act: -0.0000

Data Index: 475804 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2635. Min Act: -0.0000

Data Index: 394941 (The Pile)

Max Activating Token Index: 413

Text #6

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1797763 (The Pile)

Max Activating Token Index: 533

Text #7

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2377. Min Act: -0.0000

Data Index: 619469 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2502. Min Act: -0.0000

Data Index: 30569 (The Pile)

Max Activating Token Index: 393

Text #9

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1023307 (The Pile)

Max Activating Token Index: 407

Text #10

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2284. Min Act: -0.0000

Data Index: 17390 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2462. Min Act: -0.0000

Data Index: 804292 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1796529 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1207935 (The Pile)

Max Activating Token Index: 99

Text #14

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2225. Min Act: -0.0000

Data Index: 866768 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2453. Min Act: -0.0000

Data Index: 560417 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1568440 (The Pile)

Max Activating Token Index: 536

Text #17

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2501. Min Act: -0.0000

Data Index: 392211 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2292. Min Act: -0.0000

Data Index: 483499 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1922137 (The Pile)

Max Activating Token Index: 76