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

Dataset: The Pile

Neuron 324 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: 1.4642. Min Range: -1.4642

Max Act: 1.4642. Min Act: -0.0000

Data Index: 73419 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.2475. Min Act: -0.0000

Data Index: 153682 (The Pile)

Max Activating Token Index: 874

Text #2

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.3074. Min Act: -0.0000

Data Index: 1211406 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1476210 (The Pile)

Max Activating Token Index: 225

Text #4

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0472. Min Act: -0.0000

Data Index: 115310 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.1956. Min Act: -0.0000

Data Index: 369086 (The Pile)

Max Activating Token Index: 393

Text #6

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1734367 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.1420. Min Act: -0.0000

Data Index: 647839 (The Pile)

Max Activating Token Index: 438

Text #8

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0073. Min Act: -0.0000

Data Index: 491001 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0999. Min Act: -0.0000

Data Index: 400563 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0497. Min Act: -0.0000

Data Index: 1056037 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0266. Min Act: -0.0000

Data Index: 299533 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0880. Min Act: -0.0000

Data Index: 832266 (The Pile)

Max Activating Token Index: 729

Text #13

Max Range: 1.4642. Min Range: -1.4642

Max Act: 0.9735. Min Act: -0.0000

Data Index: 536560 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0753. Min Act: -0.0000

Data Index: 375721 (The Pile)

Max Activating Token Index: 316

Text #15

Max Range: 1.4642. Min Range: -1.4642

Max Act: 0.9945. Min Act: -0.0000

Data Index: 663800 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0567. Min Act: -0.0000

Data Index: 716742 (The Pile)

Max Activating Token Index: 361

Text #17

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1447472 (The Pile)

Max Activating Token Index: 756

Text #18

Max Range: 1.4642. Min Range: -1.4642

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1995206 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0235. Min Act: -0.0000

Data Index: 652785 (The Pile)

Max Activating Token Index: 993