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

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

Neuron 1336 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: 1.6470. Min Range: -1.6470

Max Act: 1.5743. Min Act: -0.0000

Data Index: 645568 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.5976. Min Act: -0.0000

Data Index: 86670 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.5537. Min Act: -0.0000

Data Index: 469201 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.6312. Min Act: -0.0000

Data Index: 1351854 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.6470. Min Act: -0.0001

Data Index: 87640 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.5119. Min Act: -0.0000

Data Index: 62532 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.5303. Min Act: -0.0001

Data Index: 1318878 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.4934. Min Act: -0.0001

Data Index: 317727 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.4933. Min Act: -0.0000

Data Index: 157954 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.4860. Min Act: -0.0001

Data Index: 724279 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.5106. Min Act: -0.0001

Data Index: 866109 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.4231. Min Act: -0.0000

Data Index: 1186147 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.5786. Min Act: -0.0001

Data Index: 232185 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.4336. Min Act: -0.0001

Data Index: 44523 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1336877 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.4978. Min Act: -0.0000

Data Index: 587905 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.3665. Min Act: -0.0000

Data Index: 333201 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.3084. Min Act: -0.0001

Data Index: 1215274 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.3914. Min Act: -0.0001

Data Index: 1139695 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.6470. Min Range: -1.6470

Max Act: 1.3715. Min Act: -0.0000

Data Index: 199756 (C4 (Web Text))

Max Activating Token Index: 331