Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3016 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.5133. Min Act: -0.0000

Data Index: 462312 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1603515 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1727728 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1662935 (The Pile)

Max Activating Token Index: 288

Text #4

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.5141. Min Act: -0.0000

Data Index: 626144 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1758742 (The Pile)

Max Activating Token Index: 656

Text #6

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4971. Min Act: -0.0000

Data Index: 619030 (The Pile)

Max Activating Token Index: 178

Text #7

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4720. Min Act: -0.0000

Data Index: 458739 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1516097 (The Pile)

Max Activating Token Index: 508

Text #9

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4723. Min Act: -0.0000

Data Index: 815584 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4778. Min Act: -0.0000

Data Index: 952285 (The Pile)

Max Activating Token Index: 258

Text #11

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1687501 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1065199 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1470396 (The Pile)

Max Activating Token Index: 428

Text #14

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4605. Min Act: -0.0000

Data Index: 269003 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1935555 (The Pile)

Max Activating Token Index: 296

Text #16

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4562. Min Act: -0.0000

Data Index: 230769 (The Pile)

Max Activating Token Index: 305

Text #17

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4724. Min Act: -0.0000

Data Index: 714073 (The Pile)

Max Activating Token Index: 403

Text #18

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1970455 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4174. Min Act: -0.0000

Data Index: 266769 (The Pile)

Max Activating Token Index: 324