Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3045 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1219. Min Act: -0.0004

Data Index: 1270249 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1062. Min Act: -0.0004

Data Index: 1053602 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1136. Min Act: -0.0004

Data Index: 1274284 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1085. Min Act: -0.0004

Data Index: 880465 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1032. Min Act: -0.0004

Data Index: 311622 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1026. Min Act: -0.0004

Data Index: 71452 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1004. Min Act: -0.0004

Data Index: 1107345 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1030. Min Act: -0.0004

Data Index: 542499 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0946. Min Act: -0.0004

Data Index: 120839 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0983. Min Act: -0.0004

Data Index: 842521 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0946. Min Act: -0.0004

Data Index: 1187647 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0942. Min Act: -0.0004

Data Index: 277579 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0973. Min Act: -0.0004

Data Index: 188172 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0973. Min Act: -0.0004

Data Index: 1250979 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1003. Min Act: -0.0004

Data Index: 652606 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0967. Min Act: -0.0004

Data Index: 265958 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0926. Min Act: -0.0004

Data Index: 1019786 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0964. Min Act: -0.0004

Data Index: 510670 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0956. Min Act: -0.0004

Data Index: 1036365 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0946. Min Act: -0.0004

Data Index: 1235925 (C4 (Web Text))

Max Activating Token Index: 37