Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 274 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1394. Min Act: -0.0000

Data Index: 519404 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1261. Min Act: -0.0000

Data Index: 225352 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1460670 (Python Code)

Max Activating Token Index: 401

Text #3

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1041. Min Act: -0.0000

Data Index: 451429 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0996. Min Act: -0.0000

Data Index: 747280 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0951. Min Act: -0.0000

Data Index: 95616 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1186219 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0957. Min Act: -0.0000

Data Index: 267018 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0874. Min Act: -0.0000

Data Index: 770201 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1008158 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0822. Min Act: -0.0000

Data Index: 639186 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1240624 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0813. Min Act: -0.0000

Data Index: 165056 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1291893 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0863. Min Act: -0.0000

Data Index: 166486 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1131434 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0894. Min Act: -0.0000

Data Index: 938586 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1417585 (Python Code)

Max Activating Token Index: 791

Text #18

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0888. Min Act: -0.0000

Data Index: 103949 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0839. Min Act: -0.0000

Data Index: 192199 (C4 (Web Text))

Max Activating Token Index: 919