Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 778 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6566. Min Act: -0.0000

Data Index: 57568 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6053. Min Act: -0.0000

Data Index: 1122844 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.7235. Min Act: -0.0000

Data Index: 626702 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.4578. Min Act: -0.0000

Data Index: 43322 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6009. Min Act: -0.0000

Data Index: 170252 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.4026. Min Act: -0.0000

Data Index: 1054817 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.3950. Min Act: -0.0000

Data Index: 295671 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.2898. Min Act: -0.0000

Data Index: 308158 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.2635. Min Act: -0.0000

Data Index: 1234976 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.0425. Min Act: -0.0000

Data Index: 195 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.1474. Min Act: -0.0000

Data Index: 648411 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.1346. Min Act: -0.0000

Data Index: 1103276 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.1383. Min Act: -0.0000

Data Index: 983866 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.1148. Min Act: -0.0000

Data Index: 955197 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.0957. Min Act: -0.0000

Data Index: 1028814 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 2.7235. Min Range: -2.7235

Max Act: 1.9956. Min Act: -0.0000

Data Index: 1149899 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.1069. Min Act: -0.0000

Data Index: 842563 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.0921. Min Act: -0.0000

Data Index: 65158 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 2.7235. Min Range: -2.7235

Max Act: 1.9824. Min Act: -0.0000

Data Index: 1141856 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.0356. Min Act: -0.0000

Data Index: 333639 (C4 (Web Text))

Max Activating Token Index: 519