Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 844 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7753. Min Act: -0.0003

Data Index: 1325538 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7646. Min Act: -0.0003

Data Index: 518607 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7052. Min Act: -0.0003

Data Index: 212773 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6398. Min Act: -0.0003

Data Index: 552292 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7998. Min Act: -0.0003

Data Index: 214769 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6909. Min Act: -0.0003

Data Index: 639220 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7204. Min Act: -0.0003

Data Index: 1348804 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7094. Min Act: -0.0003

Data Index: 987408 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6145. Min Act: -0.0003

Data Index: 676022 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6313. Min Act: -0.0003

Data Index: 29416 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6064. Min Act: -0.0003

Data Index: 1320162 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6765. Min Act: -0.0003

Data Index: 351577 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6797. Min Act: -0.0003

Data Index: 661377 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6348. Min Act: -0.0003

Data Index: 1217333 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5702. Min Act: -0.0003

Data Index: 521792 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6130. Min Act: -0.0003

Data Index: 739205 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4958. Min Act: -0.0003

Data Index: 723515 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5608. Min Act: -0.0003

Data Index: 1143092 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5585. Min Act: -0.0003

Data Index: 1182649 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6210. Min Act: -0.0003

Data Index: 836640 (C4 (Web Text))

Max Activating Token Index: 829