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

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

Neuron 387 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1642. Min Act: -0.0001

Data Index: 547829 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1331. Min Act: -0.0001

Data Index: 832539 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1499. Min Act: -0.0001

Data Index: 107958 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1343. Min Act: -0.0001

Data Index: 963880 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1217. Min Act: -0.0001

Data Index: 296361 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1341690 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1194. Min Act: -0.0001

Data Index: 10801 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1136. Min Act: -0.0001

Data Index: 764310 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1180. Min Act: -0.0001

Data Index: 967571 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1157. Min Act: -0.0001

Data Index: 886923 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1180. Min Act: -0.0001

Data Index: 311697 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1054. Min Act: -0.0001

Data Index: 158810 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1161. Min Act: -0.0001

Data Index: 791945 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1081. Min Act: -0.0001

Data Index: 711808 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1122329 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1105. Min Act: -0.0001

Data Index: 962083 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1133. Min Act: -0.0001

Data Index: 61426 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1189. Min Act: -0.0001

Data Index: 133896 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1141101 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1128. Min Act: -0.0001

Data Index: 916754 (C4 (Web Text))

Max Activating Token Index: 375