Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3632 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.9483. Min Act: -0.0000

Data Index: 366590 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.9046. Min Act: -0.0000

Data Index: 446682 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 2.1117. Min Range: -2.1117

Max Act: 2.0219. Min Act: -0.0000

Data Index: 21515 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 2.1117. Min Range: -2.1117

Max Act: 2.1117. Min Act: -0.0000

Data Index: 610312 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.9860. Min Act: -0.0000

Data Index: 1067724 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.9802. Min Act: -0.0000

Data Index: 1248809 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.9196. Min Act: -0.0000

Data Index: 695118 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.9136. Min Act: -0.0000

Data Index: 775790 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 2.1117. Min Range: -2.1117

Max Act: 2.0102. Min Act: -0.0000

Data Index: 1333940 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.8275. Min Act: -0.0000

Data Index: 1084306 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.8174. Min Act: -0.0000

Data Index: 784962 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.8283. Min Act: -0.0000

Data Index: 299327 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.9262. Min Act: -0.0000

Data Index: 934697 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.9228. Min Act: -0.0000

Data Index: 540544 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.7887. Min Act: -0.0000

Data Index: 453346 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.7975. Min Act: -0.0000

Data Index: 423842 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.5448. Min Act: -0.0000

Data Index: 581037 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.7022. Min Act: -0.0000

Data Index: 802633 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.6336. Min Act: -0.0000

Data Index: 83784 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 2.1117. Min Range: -2.1117

Max Act: 1.5970. Min Act: -0.0000

Data Index: 290944 (C4 (Web Text))

Max Activating Token Index: 633