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

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

Neuron 4567 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.5472. Min Act: -0.0001

Data Index: 784610 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.5471. Min Act: -0.0001

Data Index: 701179 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.5377. Min Act: -0.0001

Data Index: 975787 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.5123. Min Act: -0.0001

Data Index: 7254 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.5138. Min Act: -0.0001

Data Index: 1310317 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.5077. Min Act: -0.0001

Data Index: 616114 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4919. Min Act: -0.0001

Data Index: 1091885 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4991. Min Act: -0.0001

Data Index: 13349 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4970. Min Act: -0.0001

Data Index: 691938 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4843. Min Act: -0.0001

Data Index: 1307057 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4812. Min Act: -0.0001

Data Index: 381319 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4895. Min Act: -0.0001

Data Index: 1184474 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4775. Min Act: -0.0001

Data Index: 931276 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4866. Min Act: -0.0001

Data Index: 228245 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4884. Min Act: -0.0001

Data Index: 768057 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4800. Min Act: -0.0001

Data Index: 232844 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4801. Min Act: -0.0001

Data Index: 466986 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4830. Min Act: -0.0001

Data Index: 241296 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4663. Min Act: -0.0001

Data Index: 503398 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.5472. Min Range: -0.5472

Max Act: 0.4770. Min Act: -0.0001

Data Index: 214083 (C4 (Web Text))

Max Activating Token Index: 288