Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3057 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7954. Min Act: -0.0000

Data Index: 278752 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1171321 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1078500 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6887. Min Act: -0.0000

Data Index: 531417 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6700. Min Act: -0.0000

Data Index: 646006 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6901. Min Act: -0.0000

Data Index: 581962 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6422. Min Act: -0.0000

Data Index: 293311 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6571. Min Act: -0.0000

Data Index: 678144 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6929. Min Act: -0.0000

Data Index: 986027 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1084892 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1238521 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1191584 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6616. Min Act: -0.0000

Data Index: 510348 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6573. Min Act: -0.0000

Data Index: 842869 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6369. Min Act: -0.0000

Data Index: 187023 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6505. Min Act: -0.0000

Data Index: 668962 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6173. Min Act: -0.0000

Data Index: 821040 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5975. Min Act: -0.0000

Data Index: 471460 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6347. Min Act: -0.0000

Data Index: 912511 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5998. Min Act: -0.0000

Data Index: 379218 (C4 (Web Text))

Max Activating Token Index: 111