Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4122 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3515. Min Range: -4.3515

Max Act: 4.3515. Min Act: -0.0000

Data Index: 1614722 (Python Code)

Max Activating Token Index: 677

Text #1

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.8573. Min Act: -0.0000

Data Index: 1450505 (Python Code)

Max Activating Token Index: 447

Text #2

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.8442. Min Act: -0.0000

Data Index: 1575280 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 4.3515. Min Range: -4.3515

Max Act: 4.0072. Min Act: -0.0000

Data Index: 1419002 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.7018. Min Act: -0.0000

Data Index: 1360594 (Python Code)

Max Activating Token Index: 584

Text #5

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.7029. Min Act: -0.0000

Data Index: 1515783 (Python Code)

Max Activating Token Index: 496

Text #6

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.6645. Min Act: -0.0000

Data Index: 1466363 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.5980. Min Act: -0.0000

Data Index: 1395251 (Python Code)

Max Activating Token Index: 1008

Text #8

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.3958. Min Act: -0.0000

Data Index: 1368222 (Python Code)

Max Activating Token Index: 541

Text #9

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.5877. Min Act: -0.0000

Data Index: 1476046 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.5029. Min Act: -0.0000

Data Index: 1638335 (Python Code)

Max Activating Token Index: 1018

Text #11

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.4927. Min Act: -0.0000

Data Index: 1398118 (Python Code)

Max Activating Token Index: 241

Text #12

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.2956. Min Act: -0.0000

Data Index: 1606753 (Python Code)

Max Activating Token Index: 356

Text #13

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.1225. Min Act: -0.0000

Data Index: 1538459 (Python Code)

Max Activating Token Index: 148

Text #14

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.2299. Min Act: -0.0000

Data Index: 1427572 (Python Code)

Max Activating Token Index: 829

Text #15

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.0503. Min Act: -0.0000

Data Index: 1467555 (Python Code)

Max Activating Token Index: 805

Text #16

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.1889. Min Act: -0.0000

Data Index: 1571705 (Python Code)

Max Activating Token Index: 491

Text #17

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.0250. Min Act: -0.0000

Data Index: 1388826 (Python Code)

Max Activating Token Index: 971

Text #18

Max Range: 4.3515. Min Range: -4.3515

Max Act: 2.8675. Min Act: 0.0000

Data Index: 1589333 (Python Code)

Max Activating Token Index: 158

Text #19

Max Range: 4.3515. Min Range: -4.3515

Max Act: 3.1373. Min Act: -0.0000

Data Index: 1553320 (Python Code)

Max Activating Token Index: 133