Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 932 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.8858. Min Act: -0.0001

Data Index: 177488 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.9112. Min Act: -0.0000

Data Index: 859900 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.8812. Min Act: -0.0001

Data Index: 703904 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.8182. Min Act: -0.0001

Data Index: 957530 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7878. Min Act: -0.0001

Data Index: 413938 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.8616. Min Act: -0.0001

Data Index: 1047923 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.8175. Min Act: -0.0001

Data Index: 985356 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7626. Min Act: -0.0000

Data Index: 748014 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7766. Min Act: -0.0001

Data Index: 235935 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.8097. Min Act: -0.0001

Data Index: 328921 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7577. Min Act: -0.0001

Data Index: 1013454 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7339. Min Act: -0.0001

Data Index: 702472 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.8046. Min Act: -0.0001

Data Index: 617425 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7311. Min Act: -0.0001

Data Index: 325645 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7223. Min Act: -0.0001

Data Index: 762560 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7156. Min Act: -0.0001

Data Index: 522454 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7319. Min Act: -0.0000

Data Index: 977080 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7516. Min Act: -0.0001

Data Index: 714004 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7380. Min Act: -0.0001

Data Index: 261009 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.6970. Min Act: -0.0000

Data Index: 995503 (C4 (Web Text))

Max Activating Token Index: 672