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

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

Neuron 2667 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: 1.1861. Min Range: -1.1861

Max Act: 1.1861. Min Act: -0.0000

Data Index: 680760 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 1.1861. Min Range: -1.1861

Max Act: 1.0786. Min Act: -0.0000

Data Index: 482641 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 1.1861. Min Range: -1.1861

Max Act: 1.1175. Min Act: -0.0000

Data Index: 652354 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9921. Min Act: -0.0000

Data Index: 1249432 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.1861. Min Range: -1.1861

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1349493 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9258. Min Act: -0.0000

Data Index: 314037 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9764. Min Act: -0.0000

Data Index: 912934 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9762. Min Act: -0.0000

Data Index: 849045 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9667. Min Act: -0.0000

Data Index: 458639 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9366. Min Act: -0.0000

Data Index: 567318 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1034856 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9880. Min Act: -0.0000

Data Index: 817654 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9845. Min Act: -0.0000

Data Index: 855494 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9496. Min Act: -0.0000

Data Index: 576791 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9466. Min Act: -0.0000

Data Index: 270627 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1207106 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9211. Min Act: -0.0000

Data Index: 142294 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9500. Min Act: -0.0000

Data Index: 489446 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1039511 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.1861. Min Range: -1.1861

Max Act: 0.9111. Min Act: -0.0000

Data Index: 588864 (C4 (Web Text))

Max Activating Token Index: 441