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

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

Neuron 5041 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: 3.7238. Min Range: -3.7238

Max Act: 3.7238. Min Act: -0.0000

Data Index: 1428889 (Python Code)

Max Activating Token Index: 940

Text #1

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6442. Min Act: -0.0000

Data Index: 1463761 (Python Code)

Max Activating Token Index: 943

Text #2

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.2458. Min Act: -0.0000

Data Index: 1619707 (Python Code)

Max Activating Token Index: 873

Text #3

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.9492. Min Act: -0.0000

Data Index: 1445607 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.2122. Min Act: -0.0000

Data Index: 1510646 (Python Code)

Max Activating Token Index: 991

Text #5

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.1706. Min Act: -0.0000

Data Index: 1410560 (Python Code)

Max Activating Token Index: 777

Text #6

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.0454. Min Act: -0.0000

Data Index: 1535681 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.8713. Min Act: -0.0000

Data Index: 1450452 (Python Code)

Max Activating Token Index: 583

Text #8

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.8541. Min Act: -0.0000

Data Index: 1635048 (Python Code)

Max Activating Token Index: 971

Text #9

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.6868. Min Act: -0.0000

Data Index: 1462331 (Python Code)

Max Activating Token Index: 779

Text #10

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.8126. Min Act: -0.0000

Data Index: 1541252 (Python Code)

Max Activating Token Index: 970

Text #11

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.8200. Min Act: -0.0000

Data Index: 1499184 (Python Code)

Max Activating Token Index: 156

Text #12

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.6698. Min Act: -0.0000

Data Index: 1581084 (Python Code)

Max Activating Token Index: 901

Text #13

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.9389. Min Act: -0.0000

Data Index: 1443413 (Python Code)

Max Activating Token Index: 889

Text #14

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.7882. Min Act: -0.0000

Data Index: 1480185 (Python Code)

Max Activating Token Index: 920

Text #15

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.7652. Min Act: -0.0000

Data Index: 1451922 (Python Code)

Max Activating Token Index: 908

Text #16

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.9105. Min Act: -0.0000

Data Index: 1542159 (Python Code)

Max Activating Token Index: 322

Text #17

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.6280. Min Act: -0.0000

Data Index: 1430413 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.7569. Min Act: -0.0000

Data Index: 1635455 (Python Code)

Max Activating Token Index: 521

Text #19

Max Range: 3.7238. Min Range: -3.7238

Max Act: 2.6233. Min Act: -0.0000

Data Index: 1616973 (Python Code)

Max Activating Token Index: 892