Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3066 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3081. Min Range: -1.3081

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1562012 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 1.3081. Min Range: -1.3081

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1693336 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 1.3081. Min Range: -1.3081

Max Act: 1.2027. Min Act: -0.0000

Data Index: 727317 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 1.3081. Min Range: -1.3081

Max Act: 1.1550. Min Act: -0.0000

Data Index: 966804 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.9927. Min Act: -0.0000

Data Index: 274333 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 1.3081. Min Range: -1.3081

Max Act: 1.0996. Min Act: -0.0000

Data Index: 271420 (The Pile)

Max Activating Token Index: 866

Text #6

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.8954. Min Act: -0.0000

Data Index: 185739 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 1.3081. Min Range: -1.3081

Max Act: 1.0892. Min Act: -0.0000

Data Index: 1817281 (The Pile)

Max Activating Token Index: 703

Text #8

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.9336. Min Act: -0.0000

Data Index: 547135 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.5145. Min Act: -0.0000

Data Index: 731522 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.8602. Min Act: -0.0000

Data Index: 619984 (The Pile)

Max Activating Token Index: 946

Text #11

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1560397 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.8544. Min Act: -0.0000

Data Index: 228157 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.8084. Min Act: -0.0000

Data Index: 161047 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1300819 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.7572. Min Act: -0.0000

Data Index: 465354 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.9778. Min Act: -0.0000

Data Index: 782441 (The Pile)

Max Activating Token Index: 777

Text #17

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1244363 (The Pile)

Max Activating Token Index: 591

Text #18

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1782162 (The Pile)

Max Activating Token Index: 953

Text #19

Max Range: 1.3081. Min Range: -1.3081

Max Act: 0.8221. Min Act: -0.0000

Data Index: 54582 (The Pile)

Max Activating Token Index: 379