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

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

Neuron 1040 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1053199 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2336. Min Act: -0.0000

Data Index: 83468 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2544. Min Act: -0.0000

Data Index: 243232 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2447. Min Act: -0.0001

Data Index: 383294 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2651. Min Act: -0.0001

Data Index: 694442 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2536. Min Act: -0.0001

Data Index: 95687 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2195. Min Act: -0.0001

Data Index: 251040 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2341. Min Act: -0.0001

Data Index: 277646 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2109. Min Act: -0.0000

Data Index: 592652 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2160. Min Act: -0.0000

Data Index: 26762 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2117. Min Act: -0.0001

Data Index: 82518 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1350688 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2194. Min Act: -0.0000

Data Index: 924100 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2125. Min Act: -0.0001

Data Index: 540951 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2050. Min Act: -0.0000

Data Index: 193241 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2433. Min Act: -0.0000

Data Index: 295741 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2106. Min Act: -0.0001

Data Index: 1169029 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2247. Min Act: -0.0001

Data Index: 223936 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2077. Min Act: -0.0001

Data Index: 295759 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.2651. Min Range: -0.2651

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1023585 (C4 (Web Text))

Max Activating Token Index: 670