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

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

Neuron 3137 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7890. Min Act: -0.0001

Data Index: 1549127 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.8031. Min Act: -0.0001

Data Index: 1442677 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7443. Min Act: -0.0001

Data Index: 1514227 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7576. Min Act: -0.0001

Data Index: 1529820 (Python Code)

Max Activating Token Index: 161

Text #4

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7170. Min Act: -0.0001

Data Index: 1470491 (Python Code)

Max Activating Token Index: 104

Text #5

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7309. Min Act: -0.0001

Data Index: 1614893 (Python Code)

Max Activating Token Index: 906

Text #6

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7070. Min Act: -0.0002

Data Index: 1530883 (Python Code)

Max Activating Token Index: 90

Text #7

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6872. Min Act: -0.0001

Data Index: 1578592 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7074. Min Act: -0.0001

Data Index: 1520561 (Python Code)

Max Activating Token Index: 103

Text #9

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7092. Min Act: -0.0001

Data Index: 1459598 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1610523 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6420. Min Act: -0.0001

Data Index: 1490907 (Python Code)

Max Activating Token Index: 243

Text #12

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6477. Min Act: -0.0001

Data Index: 1562873 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6679. Min Act: -0.0001

Data Index: 1612708 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7336. Min Act: -0.0001

Data Index: 1638280 (Python Code)

Max Activating Token Index: 315

Text #15

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7236. Min Act: -0.0001

Data Index: 1555461 (Python Code)

Max Activating Token Index: 96

Text #16

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6112. Min Act: -0.0001

Data Index: 1563125 (Python Code)

Max Activating Token Index: 831

Text #17

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6718. Min Act: -0.0001

Data Index: 1494374 (Python Code)

Max Activating Token Index: 968

Text #18

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6525. Min Act: -0.0001

Data Index: 1380323 (Python Code)

Max Activating Token Index: 963

Text #19

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6948. Min Act: -0.0001

Data Index: 1457467 (Python Code)

Max Activating Token Index: 268