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

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

Neuron 2324 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: 0.5018. Min Range: -0.5018

Max Act: 0.5018. Min Act: -0.0000

Data Index: 165568 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4216. Min Act: -0.0000

Data Index: 356207 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1137494 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1192706 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1357533 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1057918 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3740. Min Act: -0.0000

Data Index: 903921 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3834. Min Act: -0.0001

Data Index: 951819 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3846. Min Act: -0.0000

Data Index: 1095528 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3848. Min Act: -0.0001

Data Index: 333072 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3768. Min Act: -0.0001

Data Index: 1020726 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3811. Min Act: -0.0000

Data Index: 128019 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3756. Min Act: -0.0001

Data Index: 249898 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1309080 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3717. Min Act: -0.0001

Data Index: 665824 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1227686 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3835. Min Act: -0.0001

Data Index: 303717 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3699. Min Act: -0.0001

Data Index: 1212088 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3689. Min Act: -0.0000

Data Index: 813145 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3699. Min Act: -0.0000

Data Index: 544300 (C4 (Web Text))

Max Activating Token Index: 875