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

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

Neuron 2939 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2482. Min Range: -1.2482

Max Act: 1.2482. Min Act: -0.0001

Data Index: 1219384 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 1.2482. Min Range: -1.2482

Max Act: 1.1617. Min Act: -0.0001

Data Index: 205229 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 1.2482. Min Range: -1.2482

Max Act: 1.1754. Min Act: -0.0001

Data Index: 812746 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 1.2482. Min Range: -1.2482

Max Act: 1.0826. Min Act: -0.0001

Data Index: 585056 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 1.2482. Min Range: -1.2482

Max Act: 1.0600. Min Act: -0.0000

Data Index: 116443 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8550. Min Act: -0.0001

Data Index: 35531 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.9194. Min Act: -0.0001

Data Index: 424272 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.9006. Min Act: -0.0001

Data Index: 1638861 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8897. Min Act: -0.0001

Data Index: 729562 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.9381. Min Act: -0.0001

Data Index: 290113 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8771. Min Act: -0.0000

Data Index: 114999 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8527. Min Act: -0.0001

Data Index: 262654 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8714. Min Act: -0.0001

Data Index: 1343745 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1345883 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8798. Min Act: -0.0001

Data Index: 564908 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8203. Min Act: -0.0001

Data Index: 812921 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8423. Min Act: -0.0001

Data Index: 330794 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8171. Min Act: -0.0000

Data Index: 519136 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8439. Min Act: -0.0001

Data Index: 323168 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8363. Min Act: -0.0000

Data Index: 602233 (C4 (Web Text))

Max Activating Token Index: 885