Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1117 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.6753. Min Act: -0.0000

Data Index: 66054 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.6089. Min Act: -0.0000

Data Index: 1064469 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.0020. Min Act: -0.0000

Data Index: 1174038 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.6010. Min Act: -0.0000

Data Index: 207140 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.3868. Min Act: -0.0000

Data Index: 826171 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.5117. Min Act: -0.0000

Data Index: 555847 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.3944. Min Act: -0.0000

Data Index: 836296 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.4487. Min Act: -0.0000

Data Index: 886750 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.1918. Min Act: -0.0000

Data Index: 959351 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.1615. Min Act: -0.0000

Data Index: 547245 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.1690. Min Act: -0.0000

Data Index: 206977 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.2501. Min Act: -0.0000

Data Index: 105740 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.1226. Min Act: -0.0000

Data Index: 884989 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.0998. Min Act: -0.0000

Data Index: 1006285 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.0707. Min Act: -0.0000

Data Index: 950476 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.0376. Min Act: -0.0000

Data Index: 894097 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.9226. Min Act: -0.0000

Data Index: 277028 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.0439. Min Act: -0.0000

Data Index: 592850 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.9921. Min Act: -0.0000

Data Index: 459592 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.9942. Min Act: -0.0000

Data Index: 523445 (C4 (Web Text))

Max Activating Token Index: 739