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

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

Neuron 164 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0487. Min Act: -0.0000

Data Index: 137654 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0000

Data Index: 818722 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1100722 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1185647 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0434. Min Act: -0.0000

Data Index: 1108589 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1171305 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0402. Min Act: -0.0000

Data Index: 845925 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0417. Min Act: -0.0000

Data Index: 604855 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0383. Min Act: -0.0000

Data Index: 1110949 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0425. Min Act: -0.0000

Data Index: 433006 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0395. Min Act: -0.0000

Data Index: 370429 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1347989 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0402. Min Act: -0.0000

Data Index: 1216384 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0387. Min Act: -0.0000

Data Index: 304614 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0397. Min Act: -0.0000

Data Index: 769043 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0361. Min Act: -0.0000

Data Index: 1439162 (Python Code)

Max Activating Token Index: 810

Text #16

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0403. Min Act: -0.0000

Data Index: 56742 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0399. Min Act: -0.0000

Data Index: 1057028 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1028148 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0384. Min Act: -0.0000

Data Index: 985292 (C4 (Web Text))

Max Activating Token Index: 702