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

Dataset: The Pile

Neuron 2337 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: 3.2448. Min Range: -3.2448

Max Act: 3.1037. Min Act: -0.0000

Data Index: 486117 (The Pile)

Max Activating Token Index: 361

Text #1

Max Range: 3.2448. Min Range: -3.2448

Max Act: 3.2448. Min Act: -0.0000

Data Index: 342492 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.9205. Min Act: -0.0000

Data Index: 371532 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.6502. Min Act: -0.0000

Data Index: 115263 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.6824. Min Act: -0.0000

Data Index: 674348 (The Pile)

Max Activating Token Index: 70

Text #5

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.7803. Min Act: -0.0000

Data Index: 1105311 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.6397. Min Act: -0.0000

Data Index: 1890637 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 3.2448. Min Range: -3.2448

Max Act: 3.0106. Min Act: -0.0000

Data Index: 348074 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.5531. Min Act: -0.0000

Data Index: 51237 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.6895. Min Act: -0.0000

Data Index: 1815898 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.3003. Min Act: -0.0000

Data Index: 1209864 (The Pile)

Max Activating Token Index: 874

Text #11

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.5165. Min Act: -0.0000

Data Index: 1266588 (The Pile)

Max Activating Token Index: 314

Text #12

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.5347. Min Act: -0.0000

Data Index: 1677747 (The Pile)

Max Activating Token Index: 297

Text #13

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.3337. Min Act: -0.0000

Data Index: 1021297 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.3347. Min Act: -0.0000

Data Index: 557386 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.2098. Min Act: -0.0000

Data Index: 640848 (The Pile)

Max Activating Token Index: 841

Text #16

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.3338. Min Act: -0.0000

Data Index: 1632239 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.2697. Min Act: -0.0000

Data Index: 1715305 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.7950. Min Act: -0.0000

Data Index: 1035932 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.5140. Min Act: -0.0000

Data Index: 1413813 (The Pile)

Max Activating Token Index: 789