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

Dataset: The Pile

Neuron 1562 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: 1.0163. Min Range: -1.0163

Max Act: 1.0068. Min Act: -0.0000

Data Index: 687398 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1341836 (The Pile)

Max Activating Token Index: 593

Text #2

Max Range: 1.0163. Min Range: -1.0163

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1509705 (The Pile)

Max Activating Token Index: 935

Text #3

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1431445 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.7954. Min Act: -0.0000

Data Index: 537399 (The Pile)

Max Activating Token Index: 810

Text #5

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.8447. Min Act: -0.0000

Data Index: 687122 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1310151 (The Pile)

Max Activating Token Index: 919

Text #7

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1849469 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.7680. Min Act: -0.0000

Data Index: 964545 (The Pile)

Max Activating Token Index: 809

Text #9

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1251152 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.8303. Min Act: -0.0000

Data Index: 552482 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.7519. Min Act: -0.0000

Data Index: 996442 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1593928 (The Pile)

Max Activating Token Index: 272

Text #13

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1505221 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1191822 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1893883 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1208737 (The Pile)

Max Activating Token Index: 145

Text #17

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1922070 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1084295 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1833549 (The Pile)

Max Activating Token Index: 758