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

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

Neuron 3709 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.8084. Min Act: -0.0001

Data Index: 644971 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3162. Min Act: -0.0001

Data Index: 468689 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3072. Min Act: -0.0001

Data Index: 253064 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4265. Min Act: -0.0001

Data Index: 1089674 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2959. Min Act: -0.0001

Data Index: 271090 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1942. Min Act: -0.0001

Data Index: 630501 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1536. Min Act: -0.0001

Data Index: 308607 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1187. Min Act: -0.0001

Data Index: 107363 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1412. Min Act: -0.0001

Data Index: 1229768 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1785. Min Act: -0.0001

Data Index: 1042527 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1952. Min Act: -0.0001

Data Index: 110317 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1860. Min Act: -0.0001

Data Index: 1221404 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1143. Min Act: -0.0001

Data Index: 58050 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1057. Min Act: -0.0001

Data Index: 658971 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1094. Min Act: -0.0001

Data Index: 1230940 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1760. Min Act: -0.0001

Data Index: 385412 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1955. Min Act: -0.0001

Data Index: 468951 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1572. Min Act: -0.0001

Data Index: 1240131 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.0578. Min Act: -0.0001

Data Index: 890076 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.0876. Min Act: -0.0001

Data Index: 695210 (C4 (Web Text))

Max Activating Token Index: 966