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

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

Neuron 196 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: 1.1889. Min Range: -1.1889

Max Act: 1.1064. Min Act: -0.0001

Data Index: 1208231 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.1889. Min Act: -0.0001

Data Index: 1354494 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0302. Min Act: -0.0001

Data Index: 1336021 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.9741. Min Act: -0.0001

Data Index: 857580 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0169. Min Act: -0.0001

Data Index: 785581 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.8640. Min Act: -0.0001

Data Index: 1317784 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.8645. Min Act: -0.0001

Data Index: 341705 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.8757. Min Act: -0.0001

Data Index: 280831 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.8817. Min Act: -0.0001

Data Index: 980090 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7946. Min Act: -0.0001

Data Index: 690587 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.8227. Min Act: -0.0001

Data Index: 582622 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7683. Min Act: -0.0001

Data Index: 110534 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7824. Min Act: -0.0001

Data Index: 630127 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7354. Min Act: -0.0001

Data Index: 938631 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7852. Min Act: -0.0001

Data Index: 99473 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.8652. Min Act: -0.0001

Data Index: 326958 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7197. Min Act: -0.0001

Data Index: 138525 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7596. Min Act: -0.0001

Data Index: 473955 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7289. Min Act: -0.0001

Data Index: 974652 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7251. Min Act: -0.0001

Data Index: 269659 (C4 (Web Text))

Max Activating Token Index: 682