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

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

Neuron 2377 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5929. Min Act: -0.0000

Data Index: 1600721 (Python Code)

Max Activating Token Index: 859

Text #1

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5185. Min Act: -0.0000

Data Index: 1559837 (Python Code)

Max Activating Token Index: 937

Text #2

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.4092. Min Act: -0.0000

Data Index: 1395559 (Python Code)

Max Activating Token Index: 609

Text #3

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.3216. Min Act: -0.0000

Data Index: 1388465 (Python Code)

Max Activating Token Index: 785

Text #4

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.3641. Min Act: -0.0000

Data Index: 1531271 (Python Code)

Max Activating Token Index: 1010

Text #5

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1460569 (Python Code)

Max Activating Token Index: 828

Text #6

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.1499. Min Act: -0.0000

Data Index: 1397438 (Python Code)

Max Activating Token Index: 914

Text #7

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1585576 (Python Code)

Max Activating Token Index: 977

Text #8

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1416484 (Python Code)

Max Activating Token Index: 272

Text #9

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.2698. Min Act: -0.0000

Data Index: 1446678 (Python Code)

Max Activating Token Index: 912

Text #10

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.2811. Min Act: -0.0000

Data Index: 1393225 (Python Code)

Max Activating Token Index: 148

Text #11

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1517074 (Python Code)

Max Activating Token Index: 906

Text #12

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1480940 (Python Code)

Max Activating Token Index: 886

Text #13

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.1616. Min Act: -0.0000

Data Index: 1454360 (Python Code)

Max Activating Token Index: 385

Text #14

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.1827. Min Act: -0.0000

Data Index: 1586208 (Python Code)

Max Activating Token Index: 382

Text #15

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1372154 (Python Code)

Max Activating Token Index: 965

Text #16

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.1579. Min Act: -0.0000

Data Index: 1532111 (Python Code)

Max Activating Token Index: 983

Text #17

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.2529. Min Act: -0.0000

Data Index: 1508312 (Python Code)

Max Activating Token Index: 485

Text #18

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.2181. Min Act: -0.0000

Data Index: 1529617 (Python Code)

Max Activating Token Index: 845

Text #19

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.2060. Min Act: -0.0000

Data Index: 1598806 (Python Code)

Max Activating Token Index: 43