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

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

Neuron 4560 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: 1.4989. Min Range: -1.4989

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1097332 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.2711. Min Act: -0.0000

Data Index: 863859 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.2867. Min Act: -0.0000

Data Index: 970798 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1137139 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.0340. Min Act: -0.0000

Data Index: 408983 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.0297. Min Act: -0.0000

Data Index: 67970 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1114331 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9431. Min Act: -0.0000

Data Index: 567113 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.0344. Min Act: -0.0000

Data Index: 318425 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9511. Min Act: -0.0000

Data Index: 478553 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9717. Min Act: -0.0000

Data Index: 883334 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9336. Min Act: -0.0000

Data Index: 784068 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1255235 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9421. Min Act: -0.0000

Data Index: 692741 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1217105 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9335. Min Act: -0.0000

Data Index: 257634 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.7973. Min Act: -0.0000

Data Index: 137386 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1111413 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.8406. Min Act: -0.0000

Data Index: 794827 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.8660. Min Act: -0.0000

Data Index: 235353 (C4 (Web Text))

Max Activating Token Index: 916