Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 767 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0046. Min Act: -0.0005

Data Index: 1576832 (Python Code)

Max Activating Token Index: 78

Text #1

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1598697 (Python Code)

Max Activating Token Index: 901

Text #2

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0041. Min Act: -0.0005

Data Index: 1598904 (Python Code)

Max Activating Token Index: 280

Text #3

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0040. Min Act: -0.0005

Data Index: 1427429 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0038. Min Act: -0.0006

Data Index: 366716 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0036. Min Act: -0.0006

Data Index: 1488634 (Python Code)

Max Activating Token Index: 824

Text #6

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0036. Min Act: -0.0006

Data Index: 1611991 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0036. Min Act: -0.0005

Data Index: 1582525 (Python Code)

Max Activating Token Index: 827

Text #8

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0035. Min Act: -0.0005

Data Index: 1360945 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0035. Min Act: -0.0005

Data Index: 1578108 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0035. Min Act: -0.0005

Data Index: 1413002 (Python Code)

Max Activating Token Index: 933

Text #11

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0035. Min Act: -0.0006

Data Index: 1480237 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0034. Min Act: -0.0005

Data Index: 1384633 (Python Code)

Max Activating Token Index: 919

Text #13

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0034. Min Act: -0.0005

Data Index: 1582648 (Python Code)

Max Activating Token Index: 654

Text #14

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1497518 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0032. Min Act: -0.0006

Data Index: 1517244 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1655648 (Python Code)

Max Activating Token Index: 999

Text #17

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1529733 (Python Code)

Max Activating Token Index: 956

Text #18

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0031. Min Act: -0.0006

Data Index: 1649276 (Python Code)

Max Activating Token Index: 567

Text #19

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1601428 (Python Code)

Max Activating Token Index: 477