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

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

Neuron 287 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7440. Min Range: -6.7440

Max Act: 6.5270. Min Act: -0.0000

Data Index: 681719 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 6.7440. Min Range: -6.7440

Max Act: 6.7440. Min Act: -0.0000

Data Index: 925587 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 6.7440. Min Range: -6.7440

Max Act: 6.1272. Min Act: -0.0000

Data Index: 980064 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 6.7440. Min Range: -6.7440

Max Act: 5.7704. Min Act: -0.0000

Data Index: 508358 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 6.7440. Min Range: -6.7440

Max Act: 5.9284. Min Act: -0.0000

Data Index: 139881 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 6.7440. Min Range: -6.7440

Max Act: 5.8700. Min Act: -0.0000

Data Index: 125664 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 6.7440. Min Range: -6.7440

Max Act: 5.8806. Min Act: -0.0000

Data Index: 717086 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 6.7440. Min Range: -6.7440

Max Act: 5.4584. Min Act: -0.0000

Data Index: 346471 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 6.7440. Min Range: -6.7440

Max Act: 5.2550. Min Act: -0.0000

Data Index: 528514 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 6.7440. Min Range: -6.7440

Max Act: 5.4677. Min Act: -0.0000

Data Index: 434548 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 6.7440. Min Range: -6.7440

Max Act: 5.1586. Min Act: -0.0000

Data Index: 286134 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 6.7440. Min Range: -6.7440

Max Act: 4.8276. Min Act: -0.0000

Data Index: 1143872 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 6.7440. Min Range: -6.7440

Max Act: 4.5680. Min Act: -0.0000

Data Index: 33428 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 6.7440. Min Range: -6.7440

Max Act: 4.7274. Min Act: -0.0000

Data Index: 763085 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 6.7440. Min Range: -6.7440

Max Act: 4.7693. Min Act: -0.0000

Data Index: 438209 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 6.7440. Min Range: -6.7440

Max Act: 4.8940. Min Act: -0.0000

Data Index: 1051553 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 6.7440. Min Range: -6.7440

Max Act: 4.6893. Min Act: -0.0000

Data Index: 308926 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 6.7440. Min Range: -6.7440

Max Act: 4.8808. Min Act: -0.0000

Data Index: 501456 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 6.7440. Min Range: -6.7440

Max Act: 4.7095. Min Act: -0.0000

Data Index: 1327196 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 6.7440. Min Range: -6.7440

Max Act: 4.7137. Min Act: -0.0000

Data Index: 99175 (C4 (Web Text))

Max Activating Token Index: 519