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

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

Neuron 2225 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5442. Min Act: -0.0000

Data Index: 374553 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5555. Min Act: -0.0001

Data Index: 460993 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5618. Min Act: -0.0000

Data Index: 601712 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5900. Min Act: -0.0001

Data Index: 1185854 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5384. Min Act: -0.0001

Data Index: 614102 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5145. Min Act: -0.0000

Data Index: 58141 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1010945 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5262. Min Act: -0.0001

Data Index: 997964 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5145. Min Act: -0.0001

Data Index: 812170 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5090. Min Act: -0.0001

Data Index: 145379 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4952. Min Act: -0.0001

Data Index: 861032 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4890. Min Act: -0.0000

Data Index: 225990 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4929. Min Act: -0.0001

Data Index: 1228621 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1131964 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4565. Min Act: -0.0000

Data Index: 426996 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4405. Min Act: -0.0001

Data Index: 120637 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4545. Min Act: -0.0001

Data Index: 203786 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4355. Min Act: -0.0000

Data Index: 741225 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4117. Min Act: -0.0001

Data Index: 59517 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4317. Min Act: -0.0001

Data Index: 1328788 (C4 (Web Text))

Max Activating Token Index: 675