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

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

Neuron 2072 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2942. Min Range: -4.2942

Max Act: 4.2942. Min Act: -0.0000

Data Index: 274954 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 4.2942. Min Range: -4.2942

Max Act: 3.5845. Min Act: -0.0000

Data Index: 912591 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 4.2942. Min Range: -4.2942

Max Act: 3.7408. Min Act: -0.0000

Data Index: 858588 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 4.2942. Min Range: -4.2942

Max Act: 3.4240. Min Act: -0.0000

Data Index: 1109991 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 4.2942. Min Range: -4.2942

Max Act: 3.2505. Min Act: -0.0000

Data Index: 1289137 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.7691. Min Act: -0.0000

Data Index: 1274521 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.8955. Min Act: -0.0000

Data Index: 284784 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 4.2942. Min Range: -4.2942

Max Act: 3.0230. Min Act: -0.0000

Data Index: 894605 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.9855. Min Act: -0.0000

Data Index: 1269750 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.8073. Min Act: -0.0000

Data Index: 278325 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.3730. Min Act: -0.0000

Data Index: 341866 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.7752. Min Act: -0.0000

Data Index: 50596 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.6205. Min Act: -0.0000

Data Index: 131736 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.7342. Min Act: -0.0000

Data Index: 1089947 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.8495. Min Act: -0.0000

Data Index: 612850 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.8506. Min Act: -0.0000

Data Index: 919758 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.6496. Min Act: -0.0000

Data Index: 924959 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.5061. Min Act: -0.0000

Data Index: 525481 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.6379. Min Act: -0.0000

Data Index: 922339 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 4.2942. Min Range: -4.2942

Max Act: 2.6588. Min Act: -0.0000

Data Index: 1016012 (C4 (Web Text))

Max Activating Token Index: 412