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

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

Neuron 1005 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0238. Min Range: -1.0238

Max Act: 1.0238. Min Act: -0.0001

Data Index: 765911 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9439. Min Act: -0.0001

Data Index: 683439 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9479. Min Act: -0.0001

Data Index: 1006094 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8762. Min Act: -0.0001

Data Index: 531862 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8876. Min Act: -0.0001

Data Index: 1336913 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8169. Min Act: -0.0001

Data Index: 784486 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8471. Min Act: -0.0001

Data Index: 651785 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8397. Min Act: -0.0001

Data Index: 157165 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7996. Min Act: -0.0001

Data Index: 274710 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7711. Min Act: -0.0001

Data Index: 176931 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7949. Min Act: -0.0001

Data Index: 1306631 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7797. Min Act: -0.0001

Data Index: 618071 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1242622 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7758. Min Act: -0.0000

Data Index: 475889 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7717. Min Act: -0.0001

Data Index: 647597 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7953. Min Act: -0.0001

Data Index: 1076924 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1026939 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7585. Min Act: -0.0001

Data Index: 1067327 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7531. Min Act: -0.0000

Data Index: 63734 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7531. Min Act: -0.0001

Data Index: 1084992 (C4 (Web Text))

Max Activating Token Index: 164