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

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

Neuron 9 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: 2.0811. Min Range: -2.0811

Max Act: 2.0811. Min Act: -0.0000

Data Index: 35668 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.7553. Min Act: -0.0000

Data Index: 723853 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.7668. Min Act: -0.0000

Data Index: 673855 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.6247. Min Act: -0.0000

Data Index: 1194795 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.5939. Min Act: 0.0000

Data Index: 169931 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.5644. Min Act: -0.0000

Data Index: 556658 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.5841. Min Act: -0.0000

Data Index: 395381 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.4922. Min Act: -0.0000

Data Index: 656030 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.4744. Min Act: -0.0000

Data Index: 1237322 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.4798. Min Act: -0.0000

Data Index: 1354823 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.4837. Min Act: -0.0000

Data Index: 117957 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.4659. Min Act: 0.0000

Data Index: 1327671 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.4592. Min Act: -0.0000

Data Index: 1355415 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.3505. Min Act: 0.0000

Data Index: 1175252 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.5101. Min Act: -0.0000

Data Index: 818235 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.4081. Min Act: -0.0000

Data Index: 1046300 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.4127. Min Act: -0.0000

Data Index: 1275759 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.3113. Min Act: -0.0000

Data Index: 1139548 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.3596. Min Act: -0.0000

Data Index: 1208091 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 2.0811. Min Range: -2.0811

Max Act: 1.3431. Min Act: 0.0000

Data Index: 1244998 (C4 (Web Text))

Max Activating Token Index: 783