Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5329 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.6483. Min Range: -5.6483

Max Act: 5.6483. Min Act: 0.0000

Data Index: 1391849 (Python Code)

Max Activating Token Index: 909

Text #1

Max Range: 5.6483. Min Range: -5.6483

Max Act: 5.3708. Min Act: 0.0000

Data Index: 1559850 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 5.6483. Min Range: -5.6483

Max Act: 4.4972. Min Act: -0.0000

Data Index: 1389756 (Python Code)

Max Activating Token Index: 959

Text #3

Max Range: 5.6483. Min Range: -5.6483

Max Act: 4.4513. Min Act: 0.0000

Data Index: 1603683 (Python Code)

Max Activating Token Index: 683

Text #4

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.8915. Min Act: 0.0000

Data Index: 1527976 (Python Code)

Max Activating Token Index: 1013

Text #5

Max Range: 5.6483. Min Range: -5.6483

Max Act: 4.0839. Min Act: 0.0000

Data Index: 1398140 (Python Code)

Max Activating Token Index: 807

Text #6

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.7367. Min Act: 0.0000

Data Index: 1436924 (Python Code)

Max Activating Token Index: 194

Text #7

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.8892. Min Act: 0.0000

Data Index: 1458695 (Python Code)

Max Activating Token Index: 770

Text #8

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.6211. Min Act: 0.0000

Data Index: 1368796 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.5028. Min Act: 0.0000

Data Index: 1411019 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.6361. Min Act: 0.0000

Data Index: 1581666 (Python Code)

Max Activating Token Index: 94

Text #11

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.4405. Min Act: 0.0000

Data Index: 1378908 (Python Code)

Max Activating Token Index: 640

Text #12

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.3271. Min Act: 0.0000

Data Index: 1416021 (Python Code)

Max Activating Token Index: 101

Text #13

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.3995. Min Act: 0.0000

Data Index: 1406928 (Python Code)

Max Activating Token Index: 711

Text #14

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.3210. Min Act: -0.0000

Data Index: 1361265 (Python Code)

Max Activating Token Index: 961

Text #15

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.4261. Min Act: 0.0000

Data Index: 1645729 (Python Code)

Max Activating Token Index: 311

Text #16

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.0714. Min Act: 0.0000

Data Index: 1538534 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.3658. Min Act: 0.0000

Data Index: 1427239 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 5.6483. Min Range: -5.6483

Max Act: 2.9277. Min Act: 0.0000

Data Index: 1386448 (Python Code)

Max Activating Token Index: 984

Text #19

Max Range: 5.6483. Min Range: -5.6483

Max Act: 3.3113. Min Act: 0.0000

Data Index: 1483260 (Python Code)

Max Activating Token Index: 467