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

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

Neuron 3055 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0052. Min Range: -1.0052

Max Act: 1.0052. Min Act: -0.0001

Data Index: 1288601 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.9889. Min Act: -0.0001

Data Index: 1266486 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.9913. Min Act: -0.0001

Data Index: 169999 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.9606. Min Act: -0.0001

Data Index: 712908 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8990. Min Act: -0.0001

Data Index: 220405 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8675. Min Act: -0.0001

Data Index: 726529 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8345. Min Act: -0.0001

Data Index: 804967 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.7778. Min Act: -0.0001

Data Index: 699124 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8224. Min Act: -0.0001

Data Index: 697818 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.7484. Min Act: -0.0001

Data Index: 1095445 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8399. Min Act: -0.0001

Data Index: 31300 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8301. Min Act: -0.0001

Data Index: 575471 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8009. Min Act: -0.0001

Data Index: 920146 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8093. Min Act: -0.0001

Data Index: 948847 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8140. Min Act: -0.0001

Data Index: 1129605 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.7657. Min Act: -0.0001

Data Index: 642661 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8598. Min Act: -0.0001

Data Index: 179291 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.7827. Min Act: -0.0001

Data Index: 1547536 (Python Code)

Max Activating Token Index: 177

Text #18

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8034. Min Act: -0.0001

Data Index: 94064 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 1.0052. Min Range: -1.0052

Max Act: 0.8128. Min Act: -0.0001

Data Index: 972062 (C4 (Web Text))

Max Activating Token Index: 703