Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1727 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1163513 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2766. Min Act: -0.0000

Data Index: 989699 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2481. Min Act: -0.0000

Data Index: 261127 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1094338 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1299957 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1225199 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2027. Min Act: -0.0000

Data Index: 730748 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2080. Min Act: -0.0000

Data Index: 821027 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2058. Min Act: -0.0000

Data Index: 43333 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1929. Min Act: -0.0000

Data Index: 385565 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1747. Min Act: -0.0000

Data Index: 447278 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1524. Min Act: -0.0000

Data Index: 375937 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1157554 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1450. Min Act: -0.0000

Data Index: 897011 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1482. Min Act: -0.0000

Data Index: 60647 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1250463 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1231952 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1416. Min Act: -0.0000

Data Index: 206558 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1400. Min Act: -0.0000

Data Index: 935792 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1106690 (C4 (Web Text))

Max Activating Token Index: 879