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

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

Neuron 4191 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0015. Min Range: -1.0015

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1143114 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.9402. Min Act: -0.0000

Data Index: 1614984 (Python Code)

Max Activating Token Index: 453

Text #2

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.9307. Min Act: -0.0000

Data Index: 138531 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1142757 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.8768. Min Act: -0.0000

Data Index: 242351 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.8857. Min Act: -0.0000

Data Index: 472475 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.8805. Min Act: -0.0000

Data Index: 414434 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.8048. Min Act: -0.0000

Data Index: 674411 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.8427. Min Act: -0.0000

Data Index: 292710 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.8173. Min Act: -0.0000

Data Index: 732417 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.8273. Min Act: -0.0000

Data Index: 824062 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1063775 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.8037. Min Act: -0.0000

Data Index: 510333 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.8026. Min Act: -0.0000

Data Index: 360078 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1507153 (Python Code)

Max Activating Token Index: 367

Text #15

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7537. Min Act: -0.0000

Data Index: 60477 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1270671 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1312316 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7551. Min Act: -0.0000

Data Index: 425982 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7963. Min Act: -0.0000

Data Index: 865566 (C4 (Web Text))

Max Activating Token Index: 202