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

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

Neuron 2120 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0250. Min Range: -5.0250

Max Act: 5.0250. Min Act: -0.0001

Data Index: 1517735 (Python Code)

Max Activating Token Index: 902

Text #1

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.9330. Min Act: -0.0000

Data Index: 1389562 (Python Code)

Max Activating Token Index: 1020

Text #2

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.7309. Min Act: -0.0000

Data Index: 1437804 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.8893. Min Act: -0.0000

Data Index: 1568325 (Python Code)

Max Activating Token Index: 849

Text #4

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.5502. Min Act: -0.0000

Data Index: 1377135 (Python Code)

Max Activating Token Index: 796

Text #5

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.3652. Min Act: -0.0000

Data Index: 1503283 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.5732. Min Act: -0.0001

Data Index: 719636 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.4151. Min Act: -0.0000

Data Index: 1613497 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.7292. Min Act: -0.0000

Data Index: 1235627 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.3305. Min Act: -0.0000

Data Index: 1314446 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.3571. Min Act: -0.0000

Data Index: 1435364 (Python Code)

Max Activating Token Index: 133

Text #11

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.5074. Min Act: -0.0000

Data Index: 1507134 (Python Code)

Max Activating Token Index: 1013

Text #12

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.4741. Min Act: -0.0000

Data Index: 1473519 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.4091. Min Act: -0.0001

Data Index: 1381830 (Python Code)

Max Activating Token Index: 384

Text #14

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.4066. Min Act: -0.0000

Data Index: 1643028 (Python Code)

Max Activating Token Index: 988

Text #15

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.2153. Min Act: -0.0000

Data Index: 1456422 (Python Code)

Max Activating Token Index: 576

Text #16

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.3963. Min Act: -0.0001

Data Index: 1401030 (Python Code)

Max Activating Token Index: 358

Text #17

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.3578. Min Act: -0.0000

Data Index: 814875 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.3465. Min Act: -0.0000

Data Index: 1364567 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 5.0250. Min Range: -5.0250

Max Act: 4.1052. Min Act: -0.0001

Data Index: 1544754 (Python Code)

Max Activating Token Index: 284