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

Dataset: The Pile

Neuron 2717 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.4354. Min Act: -0.0000

Data Index: 706827 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1941265 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3844. Min Act: -0.0000

Data Index: 173727 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3802. Min Act: -0.0000

Data Index: 299976 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1829272 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1203031 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3563. Min Act: -0.0000

Data Index: 195981 (The Pile)

Max Activating Token Index: 344

Text #7

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1311921 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3318. Min Act: -0.0000

Data Index: 415346 (The Pile)

Max Activating Token Index: 243

Text #9

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1117438 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3284. Min Act: -0.0000

Data Index: 206404 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3019. Min Act: -0.0000

Data Index: 346621 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1777343 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3243. Min Act: -0.0000

Data Index: 717720 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1525788 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1830474 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3371. Min Act: 0.0000

Data Index: 1288873 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2874. Min Act: -0.0000

Data Index: 386672 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2767. Min Act: -0.0000

Data Index: 136113 (The Pile)

Max Activating Token Index: 987

Text #19

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1739091 (The Pile)

Max Activating Token Index: 866