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

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

Neuron 5414 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5104. Min Range: -2.5104

Max Act: 2.5104. Min Act: -0.0000

Data Index: 258188 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.9817. Min Act: -0.0000

Data Index: 981066 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.7732. Min Act: -0.0000

Data Index: 155740 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.7433. Min Act: -0.0000

Data Index: 239009 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.5584. Min Act: -0.0000

Data Index: 820248 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.6965. Min Act: -0.0000

Data Index: 1257194 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.6786. Min Act: -0.0000

Data Index: 303234 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.5600. Min Act: -0.0000

Data Index: 844098 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.8549. Min Act: -0.0000

Data Index: 1313729 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.3401. Min Act: -0.0000

Data Index: 201208 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.5788. Min Act: -0.0000

Data Index: 1191951 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.5336. Min Act: -0.0000

Data Index: 68711 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.4657. Min Act: -0.0000

Data Index: 4020 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.5426. Min Act: -0.0000

Data Index: 579199 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.3948. Min Act: -0.0000

Data Index: 39565 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.4687. Min Act: -0.0000

Data Index: 1216106 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.4713. Min Act: -0.0000

Data Index: 546086 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.4698. Min Act: -0.0000

Data Index: 200826 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.5388. Min Act: -0.0000

Data Index: 1343468 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 2.5104. Min Range: -2.5104

Max Act: 1.4631. Min Act: -0.0000

Data Index: 1106948 (C4 (Web Text))

Max Activating Token Index: 789