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

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

Neuron 44 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0322. Min Range: -1.0322

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1406557 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1366093 (Python Code)

Max Activating Token Index: 1016

Text #2

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1617126 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1566138 (Python Code)

Max Activating Token Index: 231

Text #4

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1402051 (Python Code)

Max Activating Token Index: 370

Text #5

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1511203 (Python Code)

Max Activating Token Index: 966

Text #6

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1637419 (Python Code)

Max Activating Token Index: 57

Text #7

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1385092 (Python Code)

Max Activating Token Index: 991

Text #8

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1624786 (Python Code)

Max Activating Token Index: 884

Text #9

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1445638 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1483965 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1364410 (Python Code)

Max Activating Token Index: 71

Text #12

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1648482 (Python Code)

Max Activating Token Index: 768

Text #13

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1553887 (Python Code)

Max Activating Token Index: 694

Text #14

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1384408 (Python Code)

Max Activating Token Index: 976

Text #15

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1487862 (Python Code)

Max Activating Token Index: 50

Text #16

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1551397 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1453398 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1371871 (Python Code)

Max Activating Token Index: 803

Text #19

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1531495 (Python Code)

Max Activating Token Index: 66