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

Dataset: The Pile

Neuron 1484 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: 4.3314. Min Range: -4.3314

Max Act: 4.3314. Min Act: -0.0000

Data Index: 722537 (The Pile)

Max Activating Token Index: 853

Text #1

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.6869. Min Act: -0.0000

Data Index: 247211 (The Pile)

Max Activating Token Index: 804

Text #2

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.4907. Min Act: -0.0000

Data Index: 1270637 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.6789. Min Act: -0.0000

Data Index: 835884 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.6530. Min Act: -0.0000

Data Index: 1370358 (The Pile)

Max Activating Token Index: 616

Text #5

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.3815. Min Act: -0.0000

Data Index: 809748 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.6411. Min Act: -0.0000

Data Index: 178470 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.3080. Min Act: -0.0000

Data Index: 1290341 (The Pile)

Max Activating Token Index: 388

Text #8

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.2158. Min Act: -0.0000

Data Index: 452474 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.3872. Min Act: -0.0000

Data Index: 4493 (The Pile)

Max Activating Token Index: 829

Text #10

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.1009. Min Act: -0.0000

Data Index: 118729 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.0331. Min Act: -0.0000

Data Index: 1679032 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.1745. Min Act: -0.0000

Data Index: 1888153 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.2277. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.4079. Min Act: -0.0000

Data Index: 569132 (The Pile)

Max Activating Token Index: 704

Text #15

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.5507. Min Act: -0.0000

Data Index: 375081 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.1900. Min Act: -0.0000

Data Index: 27216 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.2188. Min Act: -0.0000

Data Index: 1979982 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 4.3314. Min Range: -4.3314

Max Act: 2.7056. Min Act: -0.0000

Data Index: 1271263 (The Pile)

Max Activating Token Index: 669

Text #19

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.1963. Min Act: -0.0000

Data Index: 1705466 (The Pile)

Max Activating Token Index: 828