Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1044 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.7718. Min Act: -0.0001

Data Index: 1425477 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.7194. Min Act: -0.0001

Data Index: 1448740 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6677. Min Act: -0.0001

Data Index: 592530 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6837. Min Act: -0.0001

Data Index: 59803 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6514. Min Act: -0.0001

Data Index: 1477401 (Python Code)

Max Activating Token Index: 429

Text #5

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6668. Min Act: -0.0001

Data Index: 1525892 (Python Code)

Max Activating Token Index: 1017

Text #6

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6865. Min Act: -0.0001

Data Index: 1529210 (Python Code)

Max Activating Token Index: 97

Text #7

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6854. Min Act: -0.0001

Data Index: 1486656 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6429. Min Act: -0.0001

Data Index: 1623354 (Python Code)

Max Activating Token Index: 285

Text #9

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6107. Min Act: -0.0001

Data Index: 1444274 (Python Code)

Max Activating Token Index: 314

Text #10

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6404. Min Act: -0.0001

Data Index: 500996 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6280. Min Act: -0.0001

Data Index: 1464174 (Python Code)

Max Activating Token Index: 686

Text #12

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6450. Min Act: -0.0001

Data Index: 1643609 (Python Code)

Max Activating Token Index: 192

Text #13

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6446. Min Act: -0.0001

Data Index: 248951 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6272. Min Act: -0.0001

Data Index: 1408583 (Python Code)

Max Activating Token Index: 900

Text #15

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6433. Min Act: -0.0001

Data Index: 1514130 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6131. Min Act: -0.0001

Data Index: 1574716 (Python Code)

Max Activating Token Index: 574

Text #17

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6521. Min Act: -0.0001

Data Index: 1537619 (Python Code)

Max Activating Token Index: 689

Text #18

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5735. Min Act: -0.0001

Data Index: 1653664 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5396. Min Act: -0.0001

Data Index: 1639475 (Python Code)

Max Activating Token Index: 159