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

Dataset: The Pile

Neuron 2028 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: 0.7510. Min Range: -0.7510

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1973282 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1181025 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1864103 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6401. Min Act: -0.0000

Data Index: 148911 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4984. Min Act: -0.0000

Data Index: 569539 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5629. Min Act: -0.0000

Data Index: 227943 (The Pile)

Max Activating Token Index: 811

Text #6

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1681630 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5771. Min Act: -0.0000

Data Index: 722311 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1897653 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1371154 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5989. Min Act: -0.0000

Data Index: 467676 (The Pile)

Max Activating Token Index: 497

Text #11

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5703. Min Act: -0.0000

Data Index: 631747 (The Pile)

Max Activating Token Index: 898

Text #12

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1492458 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1751214 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1472908 (The Pile)

Max Activating Token Index: 427

Text #15

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1315707 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1216616 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1366286 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5239. Min Act: -0.0000

Data Index: 209114 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5621. Min Act: -0.0000

Data Index: 654918 (The Pile)

Max Activating Token Index: 997