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

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

Neuron 239 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3866. Min Range: -2.3866

Max Act: 2.3866. Min Act: -0.0000

Data Index: 859159 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.9485. Min Act: -0.0000

Data Index: 1140737 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.9815. Min Act: -0.0000

Data Index: 712031 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.7433. Min Act: -0.0000

Data Index: 1120366 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.7441. Min Act: -0.0000

Data Index: 1226026 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.6651. Min Act: -0.0000

Data Index: 780060 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.7379. Min Act: -0.0000

Data Index: 689627 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.6271. Min Act: -0.0000

Data Index: 226816 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.6353. Min Act: -0.0000

Data Index: 888377 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.5999. Min Act: -0.0000

Data Index: 614249 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.5085. Min Act: -0.0000

Data Index: 1236695 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.6829. Min Act: -0.0000

Data Index: 453239 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.4743. Min Act: -0.0000

Data Index: 1301542 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.4933. Min Act: -0.0000

Data Index: 844794 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.4745. Min Act: -0.0000

Data Index: 51361 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.3810. Min Act: 0.0000

Data Index: 283528 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.4608. Min Act: -0.0000

Data Index: 1070939 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.4518. Min Act: -0.0000

Data Index: 714123 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.4317. Min Act: -0.0000

Data Index: 1025531 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 2.3866. Min Range: -2.3866

Max Act: 1.4192. Min Act: -0.0000

Data Index: 611174 (C4 (Web Text))

Max Activating Token Index: 60