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

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

Neuron 4733 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.1852. Min Act: -0.0001

Data Index: 1236064 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.2455. Min Act: -0.0001

Data Index: 1085173 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.4844. Min Act: -0.0001

Data Index: 1059512 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.0037. Min Act: -0.0001

Data Index: 236262 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.1288. Min Act: -0.0001

Data Index: 129426 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 5.5930. Min Range: -5.5930

Max Act: 4.9098. Min Act: -0.0001

Data Index: 387629 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.5930. Min Act: -0.0001

Data Index: 451608 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.0559. Min Act: -0.0001

Data Index: 668927 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.1948. Min Act: -0.0001

Data Index: 400213 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 5.5930. Min Range: -5.5930

Max Act: 4.9991. Min Act: -0.0001

Data Index: 415192 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 5.5930. Min Range: -5.5930

Max Act: 4.9743. Min Act: -0.0001

Data Index: 804700 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.1063. Min Act: -0.0001

Data Index: 578308 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 5.5930. Min Range: -5.5930

Max Act: 4.9622. Min Act: -0.0001

Data Index: 208565 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 5.5930. Min Range: -5.5930

Max Act: 4.7270. Min Act: -0.0001

Data Index: 1301113 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.2459. Min Act: -0.0001

Data Index: 1057312 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 5.5930. Min Range: -5.5930

Max Act: 4.8739. Min Act: -0.0001

Data Index: 518304 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.0702. Min Act: -0.0001

Data Index: 702864 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.0096. Min Act: -0.0001

Data Index: 357688 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.0044. Min Act: -0.0001

Data Index: 109309 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 5.5930. Min Range: -5.5930

Max Act: 5.1402. Min Act: -0.0001

Data Index: 767955 (C4 (Web Text))

Max Activating Token Index: 880