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

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

Neuron 1053 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: 0.6691. Min Range: -0.6691

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1140427 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.6208. Min Act: -0.0001

Data Index: 1070598 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1225481 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.5731. Min Act: -0.0000

Data Index: 970105 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.5139. Min Act: -0.0000

Data Index: 236731 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.5270. Min Act: -0.0000

Data Index: 245350 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1206676 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.5307. Min Act: -0.0000

Data Index: 401491 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.4971. Min Act: -0.0000

Data Index: 457430 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.5046. Min Act: -0.0001

Data Index: 108241 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.5182. Min Act: -0.0001

Data Index: 666875 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.4906. Min Act: -0.0001

Data Index: 138203 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.4978. Min Act: -0.0001

Data Index: 1356284 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1065284 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1300564 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.4798. Min Act: -0.0000

Data Index: 35582 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1272281 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.4938. Min Act: -0.0000

Data Index: 249953 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1047701 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.6691. Min Range: -0.6691

Max Act: 0.4750. Min Act: -0.0000

Data Index: 925899 (C4 (Web Text))

Max Activating Token Index: 388