Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2084 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2972. Min Act: -0.0000

Data Index: 105912 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2662. Min Act: -0.0000

Data Index: 706651 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2556. Min Act: -0.0000

Data Index: 738842 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2532. Min Act: -0.0000

Data Index: 228944 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2279. Min Act: -0.0000

Data Index: 28964 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2145. Min Act: -0.0000

Data Index: 352768 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1114282 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.1987. Min Act: -0.0000

Data Index: 828578 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2048. Min Act: -0.0000

Data Index: 930400 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2042. Min Act: -0.0000

Data Index: 186561 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2046. Min Act: -0.0000

Data Index: 530337 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.1930. Min Act: -0.0000

Data Index: 332804 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.1997. Min Act: -0.0000

Data Index: 999520 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.1931. Min Act: -0.0000

Data Index: 217346 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.1983. Min Act: -0.0000

Data Index: 837798 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.1890. Min Act: -0.0000

Data Index: 449157 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.1833. Min Act: -0.0000

Data Index: 332771 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1294059 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.1925. Min Act: -0.0000

Data Index: 810140 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.1918. Min Act: -0.0000

Data Index: 290446 (C4 (Web Text))

Max Activating Token Index: 106