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

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

Neuron 4675 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0426. Min Range: -1.0426

Max Act: 1.0426. Min Act: -0.0000

Data Index: 274661 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7698. Min Act: -0.0000

Data Index: 388861 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.8231. Min Act: -0.0000

Data Index: 115286 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7406. Min Act: -0.0000

Data Index: 300077 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7216. Min Act: -0.0000

Data Index: 407838 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1101119 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1027279 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7200. Min Act: -0.0000

Data Index: 588938 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6663. Min Act: -0.0000

Data Index: 655103 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6657. Min Act: -0.0000

Data Index: 862121 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6643. Min Act: -0.0000

Data Index: 854387 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1050264 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6210. Min Act: -0.0000

Data Index: 698901 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1235192 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.5929. Min Act: -0.0000

Data Index: 366611 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6308. Min Act: -0.0000

Data Index: 124595 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6207. Min Act: -0.0000

Data Index: 912248 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1137765 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6161. Min Act: -0.0000

Data Index: 111143 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6289. Min Act: -0.0000

Data Index: 549338 (C4 (Web Text))

Max Activating Token Index: 493