Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3197 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.7010. Min Act: -0.0001

Data Index: 592519 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.5304. Min Act: -0.0001

Data Index: 305503 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.4575. Min Act: -0.0001

Data Index: 291807 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.3223. Min Act: -0.0001

Data Index: 656119 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.4100. Min Act: -0.0001

Data Index: 1306229 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.4938. Min Act: -0.0001

Data Index: 47932 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.2667. Min Act: -0.0001

Data Index: 1296023 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.3489. Min Act: -0.0001

Data Index: 456990 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.3176. Min Act: -0.0001

Data Index: 1345532 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.3478. Min Act: -0.0001

Data Index: 75405 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.3723. Min Act: -0.0001

Data Index: 791202 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.2855. Min Act: -0.0001

Data Index: 1321721 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.2942. Min Act: -0.0001

Data Index: 91713 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.2160. Min Act: -0.0001

Data Index: 97829 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.2550. Min Act: -0.0001

Data Index: 479673 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.2465. Min Act: -0.0001

Data Index: 350251 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.2672. Min Act: -0.0001

Data Index: 949134 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.2412. Min Act: -0.0001

Data Index: 431253 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.2951. Min Act: -0.0001

Data Index: 132278 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.2119. Min Act: -0.0001

Data Index: 541527 (C4 (Web Text))

Max Activating Token Index: 983