Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1052 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1601. Min Act: -0.0002

Data Index: 1126534 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1541. Min Act: -0.0002

Data Index: 524581 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1447. Min Act: -0.0002

Data Index: 337076 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1370. Min Act: -0.0002

Data Index: 969167 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1366. Min Act: -0.0002

Data Index: 372126 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1293. Min Act: -0.0002

Data Index: 982212 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1226. Min Act: -0.0002

Data Index: 773390 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1203. Min Act: -0.0002

Data Index: 1293744 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1161. Min Act: -0.0002

Data Index: 1246518 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1172. Min Act: -0.0002

Data Index: 471779 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1119. Min Act: -0.0002

Data Index: 450159 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1169. Min Act: -0.0002

Data Index: 917539 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1143. Min Act: -0.0002

Data Index: 149411 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1128. Min Act: -0.0002

Data Index: 469589 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1087. Min Act: -0.0002

Data Index: 574384 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1121. Min Act: -0.0002

Data Index: 503606 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1116. Min Act: -0.0002

Data Index: 968463 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1084204 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1083. Min Act: -0.0002

Data Index: 792205 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1069. Min Act: -0.0002

Data Index: 1069955 (C4 (Web Text))

Max Activating Token Index: 42