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

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

Neuron 1022 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1943. Min Act: -0.0000

Data Index: 588516 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1069622 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1570. Min Act: -0.0000

Data Index: 624592 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1494. Min Act: -0.0000

Data Index: 63360 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1485. Min Act: -0.0000

Data Index: 627106 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1343173 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1248696 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1100653 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1163. Min Act: -0.0000

Data Index: 570037 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1187. Min Act: -0.0000

Data Index: 926443 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1040729 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1074. Min Act: -0.0000

Data Index: 73538 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1147236 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1264173 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1120. Min Act: -0.0000

Data Index: 633903 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1072. Min Act: -0.0000

Data Index: 72996 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1067140 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1076203 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1129. Min Act: -0.0000

Data Index: 367535 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1156. Min Act: -0.0000

Data Index: 477973 (C4 (Web Text))

Max Activating Token Index: 391