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

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

Neuron 3092 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1470779 (Python Code)

Max Activating Token Index: 416

Text #1

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1408037 (Python Code)

Max Activating Token Index: 819

Text #2

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1567346 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8937. Min Act: -0.0000

Data Index: 553859 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8045. Min Act: -0.0000

Data Index: 754786 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1589118 (Python Code)

Max Activating Token Index: 957

Text #6

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8176. Min Act: -0.0000

Data Index: 869638 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8282. Min Act: -0.0000

Data Index: 671967 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8171. Min Act: -0.0000

Data Index: 988925 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7964. Min Act: -0.0000

Data Index: 748888 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7671. Min Act: -0.0000

Data Index: 870084 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1542492 (Python Code)

Max Activating Token Index: 796

Text #12

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1496876 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1030434 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7269. Min Act: -0.0000

Data Index: 204120 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1602029 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1257071 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1098823 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7360. Min Act: -0.0000

Data Index: 888391 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7379. Min Act: -0.0000

Data Index: 38492 (C4 (Web Text))

Max Activating Token Index: 375