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

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

Neuron 546 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.4321. Min Act: -0.0000

Data Index: 626378 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.3249. Min Act: -0.0000

Data Index: 58800 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1131890 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1119921 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.2173. Min Act: -0.0000

Data Index: 704962 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.2106. Min Act: -0.0000

Data Index: 137148 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1629253 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.2134. Min Act: -0.0000

Data Index: 671358 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.0893. Min Act: -0.0000

Data Index: 67124 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1226361 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1040205 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.0916. Min Act: -0.0000

Data Index: 1244723 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.0606. Min Act: -0.0000

Data Index: 141532 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.0252. Min Act: 0.0000

Data Index: 1413224 (Python Code)

Max Activating Token Index: 118

Text #14

Max Range: 1.4321. Min Range: -1.4321

Max Act: 0.9204. Min Act: -0.0000

Data Index: 453627 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 1.4321. Min Range: -1.4321

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1613464 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.0235. Min Act: -0.0000

Data Index: 259409 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.4321. Min Range: -1.4321

Max Act: 1.1131. Min Act: -0.0000

Data Index: 629966 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 1.4321. Min Range: -1.4321

Max Act: 0.9714. Min Act: -0.0000

Data Index: 135853 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.4321. Min Range: -1.4321

Max Act: 0.9819. Min Act: -0.0000

Data Index: 547875 (C4 (Web Text))

Max Activating Token Index: 994