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

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

Neuron 2202 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: 0.8522. Min Range: -0.8522

Max Act: 0.8522. Min Act: -0.0000

Data Index: 27946 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.8491. Min Act: -0.0000

Data Index: 44685 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.8184. Min Act: -0.0000

Data Index: 349064 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.7640. Min Act: -0.0000

Data Index: 848601 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.7744. Min Act: -0.0000

Data Index: 332034 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.7074. Min Act: -0.0000

Data Index: 332039 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6796. Min Act: -0.0000

Data Index: 393235 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1350856 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1181854 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6616. Min Act: -0.0000

Data Index: 92979 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6112. Min Act: -0.0000

Data Index: 102629 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6401. Min Act: -0.0000

Data Index: 504028 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6082. Min Act: -0.0000

Data Index: 339403 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6058. Min Act: -0.0000

Data Index: 442560 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6006. Min Act: -0.0000

Data Index: 730724 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6675. Min Act: -0.0000

Data Index: 943065 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6055. Min Act: -0.0000

Data Index: 578971 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.5989. Min Act: -0.0000

Data Index: 843758 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6017. Min Act: -0.0000

Data Index: 573727 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1202504 (C4 (Web Text))

Max Activating Token Index: 519