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

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

Neuron 2856 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1048665 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.3345. Min Act: -0.0000

Data Index: 179504 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.3271. Min Act: -0.0000

Data Index: 789646 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.3279. Min Act: -0.0000

Data Index: 310475 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2860. Min Act: -0.0000

Data Index: 166994 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1316933 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.3110. Min Act: -0.0000

Data Index: 987916 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.3045. Min Act: -0.0000

Data Index: 919948 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2701. Min Act: -0.0000

Data Index: 476726 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2816. Min Act: -0.0000

Data Index: 731477 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2876. Min Act: -0.0000

Data Index: 420990 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1130160 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1015761 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2719. Min Act: -0.0000

Data Index: 112096 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2407. Min Act: -0.0000

Data Index: 933576 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2686. Min Act: -0.0000

Data Index: 346637 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2680. Min Act: -0.0000

Data Index: 227550 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2821. Min Act: -0.0000

Data Index: 629171 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2532. Min Act: -0.0000

Data Index: 622013 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2580. Min Act: -0.0000

Data Index: 1325261 (C4 (Web Text))

Max Activating Token Index: 155