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

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

Neuron 4154 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2300. Min Act: -0.0001

Data Index: 63652 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2174. Min Act: -0.0001

Data Index: 79201 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2140. Min Act: -0.0001

Data Index: 303306 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2137. Min Act: -0.0001

Data Index: 448805 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2142. Min Act: -0.0001

Data Index: 766528 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2133. Min Act: -0.0001

Data Index: 104601 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2110. Min Act: -0.0001

Data Index: 578911 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2077. Min Act: -0.0001

Data Index: 193686 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2091. Min Act: -0.0001

Data Index: 464106 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2073. Min Act: -0.0001

Data Index: 579033 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2041. Min Act: -0.0001

Data Index: 323782 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2059. Min Act: -0.0001

Data Index: 887061 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2047. Min Act: -0.0001

Data Index: 823938 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2047. Min Act: -0.0001

Data Index: 156043 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2076. Min Act: -0.0001

Data Index: 795182 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2054. Min Act: -0.0001

Data Index: 1254871 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2071. Min Act: -0.0001

Data Index: 40083 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1998. Min Act: -0.0001

Data Index: 473588 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1992. Min Act: -0.0001

Data Index: 466751 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2026. Min Act: -0.0001

Data Index: 68241 (C4 (Web Text))

Max Activating Token Index: 924