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

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

Neuron 998 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: 1.4894. Min Range: -1.4894

Max Act: 1.4894. Min Act: -0.0000

Data Index: 856441 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.4169. Min Act: -0.0000

Data Index: 408860 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.2971. Min Act: -0.0000

Data Index: 31791 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.3826. Min Act: -0.0000

Data Index: 85910 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.2495. Min Act: -0.0000

Data Index: 252807 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.2419. Min Act: -0.0000

Data Index: 978367 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.1901. Min Act: -0.0000

Data Index: 407774 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.2504. Min Act: -0.0000

Data Index: 372140 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.1649. Min Act: -0.0000

Data Index: 336981 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0712. Min Act: -0.0000

Data Index: 365791 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.1372. Min Act: -0.0000

Data Index: 116160 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.1395. Min Act: -0.0000

Data Index: 716244 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0604. Min Act: -0.0000

Data Index: 106446 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1276911 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0570. Min Act: -0.0000

Data Index: 1252239 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.1552. Min Act: -0.0000

Data Index: 341289 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0780. Min Act: -0.0000

Data Index: 820435 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0238. Min Act: -0.0000

Data Index: 663949 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1257832 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0342. Min Act: -0.0000

Data Index: 388923 (C4 (Web Text))

Max Activating Token Index: 381