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

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

Neuron 3644 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.1600. Min Act: -0.0000

Data Index: 559707 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1234311 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9876. Min Act: -0.0000

Data Index: 323917 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9761. Min Act: -0.0000

Data Index: 143150 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9043. Min Act: -0.0000

Data Index: 553529 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8960. Min Act: -0.0000

Data Index: 744343 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9708. Min Act: -0.0000

Data Index: 431694 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8594. Min Act: -0.0000

Data Index: 691772 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1525264 (Python Code)

Max Activating Token Index: 782

Text #9

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1549358 (Python Code)

Max Activating Token Index: 457

Text #10

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9059. Min Act: -0.0000

Data Index: 606654 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8746. Min Act: -0.0000

Data Index: 400786 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1319704 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1122144 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1481523 (Python Code)

Max Activating Token Index: 871

Text #15

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8322. Min Act: -0.0000

Data Index: 192216 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8480. Min Act: -0.0000

Data Index: 308607 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1589892 (Python Code)

Max Activating Token Index: 950

Text #18

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1510344 (Python Code)

Max Activating Token Index: 469

Text #19

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8581. Min Act: -0.0001

Data Index: 172131 (C4 (Web Text))

Max Activating Token Index: 959