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

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

Neuron 2326 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0072. Min Act: -0.0003

Data Index: 345972 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1201239 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0066. Min Act: -0.0003

Data Index: 439273 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0066. Min Act: -0.0003

Data Index: 977479 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0066. Min Act: -0.0003

Data Index: 993796 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1063510 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0003

Data Index: 406843 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1062720 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1188717 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0063. Min Act: -0.0003

Data Index: 290162 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0063. Min Act: -0.0003

Data Index: 130211 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0063. Min Act: -0.0003

Data Index: 546621 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1232923 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0063. Min Act: -0.0003

Data Index: 970315 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1219008 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1299816 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1045077 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0062. Min Act: -0.0003

Data Index: 815364 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0061. Min Act: -0.0003

Data Index: 278387 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0061. Min Act: -0.0003

Data Index: 328228 (C4 (Web Text))

Max Activating Token Index: 10