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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3540 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.7667. Min Act: -0.0001

Data Index: 620121 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.5532. Min Act: -0.0000

Data Index: 538635 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.5037. Min Act: -0.0000

Data Index: 893511 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.6659. Min Act: -0.0000

Data Index: 389740 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.4485. Min Act: -0.0000

Data Index: 843551 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.4130. Min Act: -0.0001

Data Index: 1069471 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.5197. Min Act: -0.0001

Data Index: 1027060 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.4907. Min Act: -0.0000

Data Index: 926487 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.2886. Min Act: -0.0001

Data Index: 1050110 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.2776. Min Act: -0.0001

Data Index: 677656 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.2643. Min Act: -0.0000

Data Index: 231507 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.2330. Min Act: -0.0001

Data Index: 131647 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.3748. Min Act: -0.0001

Data Index: 254238 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.0356. Min Act: -0.0000

Data Index: 898708 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.2019. Min Act: -0.0001

Data Index: 661778 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.1938. Min Act: -0.0001

Data Index: 242197 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.1724. Min Act: -0.0000

Data Index: 1358932 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.1368. Min Act: -0.0000

Data Index: 1345935 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 3.7667. Min Range: -3.7667

Max Act: 2.9921. Min Act: -0.0000

Data Index: 390665 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 3.7667. Min Range: -3.7667

Max Act: 3.1035. Min Act: -0.0000

Data Index: 1199942 (C4 (Web Text))

Max Activating Token Index: 936