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

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

Neuron 3761 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: 2.0074. Min Range: -2.0074

Max Act: 1.9841. Min Act: -0.0000

Data Index: 320240 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 2.0074. Min Range: -2.0074

Max Act: 2.0074. Min Act: -0.0000

Data Index: 1211106 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.8493. Min Act: -0.0000

Data Index: 302254 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.8432. Min Act: -0.0000

Data Index: 325113 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.7354. Min Act: -0.0000

Data Index: 534408 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.7018. Min Act: -0.0000

Data Index: 613509 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.6839. Min Act: -0.0000

Data Index: 702598 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.6772. Min Act: -0.0000

Data Index: 1189462 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.6760. Min Act: -0.0000

Data Index: 1114741 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.6497. Min Act: -0.0000

Data Index: 606455 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.6374. Min Act: -0.0000

Data Index: 1260166 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.6103. Min Act: -0.0000

Data Index: 887818 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.5635. Min Act: -0.0000

Data Index: 749575 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.5371. Min Act: -0.0000

Data Index: 598381 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.5205. Min Act: -0.0000

Data Index: 702043 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.5154. Min Act: -0.0000

Data Index: 937329 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.5125. Min Act: -0.0000

Data Index: 599247 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.4985. Min Act: -0.0000

Data Index: 58870 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.5022. Min Act: -0.0000

Data Index: 366660 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 2.0074. Min Range: -2.0074

Max Act: 1.4858. Min Act: -0.0000

Data Index: 1357999 (C4 (Web Text))

Max Activating Token Index: 742