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

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

Neuron 630 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: 0.9578. Min Range: -0.9578

Max Act: 0.9578. Min Act: -0.0001

Data Index: 1647252 (Python Code)

Max Activating Token Index: 105

Text #1

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7824. Min Act: -0.0001

Data Index: 1499807 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7317. Min Act: -0.0001

Data Index: 1640786 (Python Code)

Max Activating Token Index: 296

Text #3

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1602152 (Python Code)

Max Activating Token Index: 338

Text #4

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.7104. Min Act: -0.0001

Data Index: 1649974 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6710. Min Act: -0.0001

Data Index: 1441750 (Python Code)

Max Activating Token Index: 526

Text #6

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6397. Min Act: -0.0001

Data Index: 1568263 (Python Code)

Max Activating Token Index: 713

Text #7

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1534513 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6348. Min Act: -0.0001

Data Index: 1615774 (Python Code)

Max Activating Token Index: 552

Text #9

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6710. Min Act: -0.0001

Data Index: 1498472 (Python Code)

Max Activating Token Index: 503

Text #10

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1508566 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1545503 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6414. Min Act: -0.0001

Data Index: 1598019 (Python Code)

Max Activating Token Index: 546

Text #13

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1369793 (Python Code)

Max Activating Token Index: 423

Text #14

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6382. Min Act: -0.0001

Data Index: 1521485 (Python Code)

Max Activating Token Index: 105

Text #15

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1375873 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1390630 (Python Code)

Max Activating Token Index: 316

Text #17

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6037. Min Act: -0.0001

Data Index: 1609061 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1514099 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 0.9578. Min Range: -0.9578

Max Act: 0.5792. Min Act: -0.0001

Data Index: 1644795 (Python Code)

Max Activating Token Index: 79