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

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

Neuron 2926 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.8629. Min Act: -0.0000

Data Index: 1458732 (Python Code)

Max Activating Token Index: 140

Text #1

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.8529. Min Act: -0.0000

Data Index: 1399557 (Python Code)

Max Activating Token Index: 61

Text #2

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.8362. Min Act: -0.0000

Data Index: 168281 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.8517. Min Act: -0.0000

Data Index: 1518374 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.8553. Min Act: -0.0000

Data Index: 1625875 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.7136. Min Act: -0.0000

Data Index: 1574111 (Python Code)

Max Activating Token Index: 80

Text #6

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.8417. Min Act: -0.0000

Data Index: 1481475 (Python Code)

Max Activating Token Index: 77

Text #7

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.6985. Min Act: -0.0000

Data Index: 1426884 (Python Code)

Max Activating Token Index: 71

Text #8

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.8319. Min Act: -0.0000

Data Index: 1617083 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.7197. Min Act: -0.0000

Data Index: 1529273 (Python Code)

Max Activating Token Index: 69

Text #10

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.7057. Min Act: -0.0000

Data Index: 1485336 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.7100. Min Act: -0.0000

Data Index: 1468157 (Python Code)

Max Activating Token Index: 55

Text #12

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.4267. Min Act: -0.0000

Data Index: 1590631 (Python Code)

Max Activating Token Index: 971

Text #13

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.5027. Min Act: -0.0000

Data Index: 741784 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.5926. Min Act: -0.0000

Data Index: 1489834 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.5999. Min Act: -0.0000

Data Index: 1557942 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.4512. Min Act: -0.0000

Data Index: 1553706 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.5847. Min Act: -0.0000

Data Index: 1523663 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.5819. Min Act: -0.0000

Data Index: 1622560 (Python Code)

Max Activating Token Index: 81

Text #19

Max Range: 2.8629. Min Range: -2.8629

Max Act: 2.5490. Min Act: -0.0000

Data Index: 468446 (C4 (Web Text))

Max Activating Token Index: 568