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

Dataset: The Pile

Neuron 3397 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: 1.5474. Min Range: -1.5474

Max Act: 1.5474. Min Act: -0.0000

Data Index: 287609 (The Pile)

Max Activating Token Index: 905

Text #1

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.3642. Min Act: -0.0000

Data Index: 296626 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.3422. Min Act: -0.0000

Data Index: 1250975 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1810677 (The Pile)

Max Activating Token Index: 411

Text #4

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2132. Min Act: -0.0000

Data Index: 817896 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.1513. Min Act: -0.0000

Data Index: 18800 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1971372 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.1342. Min Act: -0.0000

Data Index: 1581853 (The Pile)

Max Activating Token Index: 105

Text #8

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.0089. Min Act: -0.0000

Data Index: 222505 (The Pile)

Max Activating Token Index: 766

Text #9

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.1303. Min Act: -0.0000

Data Index: 635162 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.1147. Min Act: -0.0000

Data Index: 601577 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1313201 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.0184. Min Act: -0.0000

Data Index: 1376228 (The Pile)

Max Activating Token Index: 72

Text #13

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1576675 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.0924. Min Act: -0.0000

Data Index: 612276 (The Pile)

Max Activating Token Index: 293

Text #15

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.0701. Min Act: -0.0000

Data Index: 718206 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.1284. Min Act: -0.0000

Data Index: 897210 (The Pile)

Max Activating Token Index: 264

Text #17

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.0489. Min Act: -0.0000

Data Index: 812153 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.0762. Min Act: -0.0000

Data Index: 396166 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.0289. Min Act: -0.0000

Data Index: 37222 (The Pile)

Max Activating Token Index: 7