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

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

Neuron 3499 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1276. Min Act: -0.0001

Data Index: 469765 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1177192 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1274. Min Act: -0.0001

Data Index: 352982 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1170034 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1230. Min Act: -0.0001

Data Index: 975427 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1285152 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0994. Min Act: -0.0001

Data Index: 511743 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1097. Min Act: -0.0001

Data Index: 60313 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1081. Min Act: -0.0001

Data Index: 698547 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1155. Min Act: -0.0001

Data Index: 651100 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1049. Min Act: -0.0001

Data Index: 215139 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0981. Min Act: -0.0001

Data Index: 935416 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0997. Min Act: -0.0001

Data Index: 236804 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1149721 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1144. Min Act: -0.0001

Data Index: 418821 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0737. Min Act: -0.0001

Data Index: 342328 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1060. Min Act: -0.0001

Data Index: 396774 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0945. Min Act: -0.0001

Data Index: 24765 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1135104 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0956. Min Act: -0.0001

Data Index: 309589 (C4 (Web Text))

Max Activating Token Index: 888