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

Dataset: The Pile

Neuron 2001 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3350. Min Act: -0.0000

Data Index: 627008 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3039. Min Act: -0.0000

Data Index: 497025 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1679213 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1509132 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2770. Min Act: -0.0000

Data Index: 986192 (The Pile)

Max Activating Token Index: 276

Text #5

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1927256 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2494. Min Act: -0.0000

Data Index: 828810 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2471. Min Act: -0.0000

Data Index: 722870 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2463. Min Act: -0.0000

Data Index: 600603 (The Pile)

Max Activating Token Index: 324

Text #9

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2432. Min Act: -0.0000

Data Index: 374504 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1539042 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2329. Min Act: -0.0000

Data Index: 818741 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1026770 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1489085 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2404. Min Act: -0.0000

Data Index: 516545 (The Pile)

Max Activating Token Index: 283

Text #15

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1740609 (The Pile)

Max Activating Token Index: 104

Text #16

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1175021 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1849455 (The Pile)

Max Activating Token Index: 943

Text #18

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2119. Min Act: -0.0000

Data Index: 241549 (The Pile)

Max Activating Token Index: 245

Text #19

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1079247 (The Pile)

Max Activating Token Index: 923