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

Dataset: The Pile

Neuron 2881 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: 0.7299. Min Range: -0.7299

Max Act: 0.7299. Min Act: 0.0000

Data Index: 540305 (The Pile)

Max Activating Token Index: 496

Text #1

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6906. Min Act: -0.0001

Data Index: 436673 (The Pile)

Max Activating Token Index: 612

Text #2

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6653. Min Act: -0.0000

Data Index: 291156 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6451. Min Act: -0.0000

Data Index: 8623 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6007. Min Act: -0.0000

Data Index: 719351 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1369005 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6080. Min Act: -0.0001

Data Index: 1508372 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1929555 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5871. Min Act: -0.0000

Data Index: 645755 (The Pile)

Max Activating Token Index: 433

Text #9

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1399296 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6050. Min Act: -0.0000

Data Index: 735150 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1294297 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1457344 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4916. Min Act: -0.0000

Data Index: 409354 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1205254 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5468. Min Act: -0.0000

Data Index: 891478 (The Pile)

Max Activating Token Index: 644

Text #16

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5578. Min Act: -0.0000

Data Index: 901190 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1098413 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1371191 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5796. Min Act: 0.0000

Data Index: 1060128 (The Pile)

Max Activating Token Index: 238