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

Dataset: The Pile

Neuron 2186 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1047467 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6509. Min Act: -0.0000

Data Index: 853031 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6234. Min Act: -0.0000

Data Index: 745282 (The Pile)

Max Activating Token Index: 628

Text #3

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6187. Min Act: -0.0000

Data Index: 745480 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5830. Min Act: -0.0000

Data Index: 820052 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5550. Min Act: -0.0000

Data Index: 31947 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1487900 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1582426 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5340. Min Act: -0.0000

Data Index: 355366 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5311. Min Act: -0.0000

Data Index: 527014 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5567. Min Act: -0.0000

Data Index: 311231 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1946630 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1511371 (The Pile)

Max Activating Token Index: 931

Text #13

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5241. Min Act: 0.0000

Data Index: 1826076 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1693047 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1584064 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1845981 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.4698. Min Act: -0.0000

Data Index: 428596 (The Pile)

Max Activating Token Index: 165

Text #18

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1520689 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1322214 (The Pile)

Max Activating Token Index: 466