Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3669 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6629. Min Act: -0.0000

Data Index: 754040 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6628. Min Act: 0.0000

Data Index: 42906 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6337. Min Act: -0.0001

Data Index: 362645 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6254. Min Act: -0.0001

Data Index: 257260 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6229. Min Act: -0.0001

Data Index: 1026528 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5800. Min Act: -0.0000

Data Index: 619697 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5790. Min Act: -0.0001

Data Index: 483054 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1349610 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4981. Min Act: -0.0001

Data Index: 867959 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5496. Min Act: -0.0001

Data Index: 804826 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5430. Min Act: -0.0001

Data Index: 761890 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5414. Min Act: -0.0000

Data Index: 621997 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5381. Min Act: -0.0001

Data Index: 388551 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5075. Min Act: -0.0001

Data Index: 354683 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4892. Min Act: -0.0001

Data Index: 1003233 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4938. Min Act: -0.0000

Data Index: 971135 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5150. Min Act: -0.0001

Data Index: 1190600 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4971. Min Act: -0.0000

Data Index: 194428 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5078. Min Act: -0.0000

Data Index: 96899 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5089. Min Act: -0.0000

Data Index: 692760 (C4 (Web Text))

Max Activating Token Index: 284