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

Dataset: The Pile

Neuron 2603 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: 0.7300. Min Range: -0.7300

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1562823 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1832117 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6719. Min Act: -0.0000

Data Index: 80505 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1695982 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1803204 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1397730 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6168. Min Act: -0.0000

Data Index: 851530 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1982255 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1801805 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6141. Min Act: -0.0000

Data Index: 354150 (The Pile)

Max Activating Token Index: 729

Text #10

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6070. Min Act: -0.0000

Data Index: 312227 (The Pile)

Max Activating Token Index: 515

Text #11

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1116223 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5572. Min Act: -0.0000

Data Index: 578770 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1881717 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5413. Min Act: -0.0000

Data Index: 233050 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1880353 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1306594 (The Pile)

Max Activating Token Index: 399

Text #17

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1053905 (The Pile)

Max Activating Token Index: 237

Text #18

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5197. Min Act: -0.0000

Data Index: 925461 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1189353 (The Pile)

Max Activating Token Index: 45