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

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

Neuron 587 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: 0.5559. Min Range: -0.5559

Max Act: 0.5559. Min Act: -0.0000

Data Index: 481962 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1303676 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1051044 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4224. Min Act: -0.0000

Data Index: 785909 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4251. Min Act: -0.0000

Data Index: 288582 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4089. Min Act: -0.0000

Data Index: 115736 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4040. Min Act: -0.0000

Data Index: 250138 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3926. Min Act: -0.0000

Data Index: 281442 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3897. Min Act: -0.0000

Data Index: 650254 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1239190 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1004897 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1071282 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3774. Min Act: -0.0000

Data Index: 471704 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1091020 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.2876. Min Act: -0.0000

Data Index: 262872 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3571. Min Act: -0.0000

Data Index: 554539 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1341891 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3607. Min Act: -0.0000

Data Index: 639018 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1299636 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1166391 (C4 (Web Text))

Max Activating Token Index: 232