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

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

Neuron 3198 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.9428. Min Act: -0.0000

Data Index: 901090 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.7958. Min Act: -0.0000

Data Index: 101594 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.7566. Min Act: -0.0000

Data Index: 838923 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6985. Min Act: -0.0000

Data Index: 63127 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.7117. Min Act: -0.0000

Data Index: 765108 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1152084 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1057277 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6837. Min Act: -0.0000

Data Index: 49435 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1259729 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6650. Min Act: -0.0000

Data Index: 79458 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6807. Min Act: -0.0000

Data Index: 341353 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1248525 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5665. Min Act: -0.0000

Data Index: 770946 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6168. Min Act: -0.0000

Data Index: 876649 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6071. Min Act: -0.0000

Data Index: 833164 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6042. Min Act: -0.0000

Data Index: 482917 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1168295 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1069588 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6089. Min Act: -0.0000

Data Index: 58630 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1322646 (C4 (Web Text))

Max Activating Token Index: 101