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

Dataset: The Pile

Neuron 4754 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: 3.6547. Min Range: -3.6547

Max Act: 3.4907. Min Act: -0.0000

Data Index: 635117 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 3.6547. Min Range: -3.6547

Max Act: 3.3766. Min Act: -0.0000

Data Index: 31949 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 3.6547. Min Range: -3.6547

Max Act: 3.6547. Min Act: -0.0000

Data Index: 1037750 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 3.6547. Min Range: -3.6547

Max Act: 3.1874. Min Act: -0.0000

Data Index: 1017571 (The Pile)

Max Activating Token Index: 807

Text #4

Max Range: 3.6547. Min Range: -3.6547

Max Act: 3.0782. Min Act: -0.0000

Data Index: 1782162 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.9353. Min Act: -0.0000

Data Index: 731522 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 3.6547. Min Range: -3.6547

Max Act: 3.4073. Min Act: -0.0000

Data Index: 1040175 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.8775. Min Act: -0.0000

Data Index: 1059350 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 3.6547. Min Range: -3.6547

Max Act: 3.0282. Min Act: -0.0000

Data Index: 1912014 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.8372. Min Act: -0.0000

Data Index: 782441 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.9643. Min Act: -0.0000

Data Index: 681134 (The Pile)

Max Activating Token Index: 943

Text #11

Max Range: 3.6547. Min Range: -3.6547

Max Act: 3.0545. Min Act: -0.0000

Data Index: 10974 (The Pile)

Max Activating Token Index: 473

Text #12

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.9109. Min Act: -0.0000

Data Index: 1314823 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.6968. Min Act: -0.0000

Data Index: 919847 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.9487. Min Act: -0.0000

Data Index: 838548 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.7152. Min Act: -0.0000

Data Index: 1346708 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.8466. Min Act: -0.0000

Data Index: 1594361 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.7360. Min Act: -0.0000

Data Index: 255297 (The Pile)

Max Activating Token Index: 141

Text #18

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.4808. Min Act: -0.0000

Data Index: 874497 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 3.6547. Min Range: -3.6547

Max Act: 2.5886. Min Act: -0.0000

Data Index: 1244363 (The Pile)

Max Activating Token Index: 661