Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4874 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2152. Min Range: -5.2152

Max Act: 5.2152. Min Act: -0.0000

Data Index: 1262033 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 5.2152. Min Range: -5.2152

Max Act: 4.5170. Min Act: -0.0000

Data Index: 1257473 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 5.2152. Min Range: -5.2152

Max Act: 4.2955. Min Act: -0.0000

Data Index: 1185103 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 5.2152. Min Range: -5.2152

Max Act: 4.1885. Min Act: -0.0000

Data Index: 1314701 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.9841. Min Act: -0.0000

Data Index: 935205 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 5.2152. Min Range: -5.2152

Max Act: 4.0659. Min Act: -0.0000

Data Index: 178280 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.8859. Min Act: -0.0000

Data Index: 202599 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 5.2152. Min Range: -5.2152

Max Act: 4.0482. Min Act: -0.0000

Data Index: 100907 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 5.2152. Min Range: -5.2152

Max Act: 4.0240. Min Act: -0.0000

Data Index: 1153563 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.8053. Min Act: -0.0000

Data Index: 1159981 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.6382. Min Act: -0.0000

Data Index: 1152742 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.7906. Min Act: -0.0000

Data Index: 1126934 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.7774. Min Act: -0.0000

Data Index: 1199241 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.9223. Min Act: -0.0000

Data Index: 886622 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.6652. Min Act: -0.0000

Data Index: 122667 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.6164. Min Act: -0.0000

Data Index: 460651 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.5992. Min Act: -0.0000

Data Index: 1297843 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.7598. Min Act: -0.0000

Data Index: 227652 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.5793. Min Act: -0.0000

Data Index: 1297974 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 5.2152. Min Range: -5.2152

Max Act: 3.5437. Min Act: -0.0000

Data Index: 1347385 (C4 (Web Text))

Max Activating Token Index: 843