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

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

Neuron 5702 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0238. Min Range: -1.0238

Max Act: 1.0238. Min Act: -0.0000

Data Index: 1102918 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8925. Min Act: -0.0000

Data Index: 362304 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9466. Min Act: -0.0000

Data Index: 205797 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8573. Min Act: -0.0000

Data Index: 841957 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8192. Min Act: -0.0000

Data Index: 180493 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7853. Min Act: -0.0000

Data Index: 340547 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8588. Min Act: -0.0000

Data Index: 64088 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7404. Min Act: -0.0000

Data Index: 488631 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8850. Min Act: -0.0000

Data Index: 982440 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7542. Min Act: -0.0000

Data Index: 388930 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7789. Min Act: -0.0000

Data Index: 314615 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7194. Min Act: -0.0000

Data Index: 860160 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1215367 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.6977. Min Act: -0.0000

Data Index: 86068 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.6673. Min Act: -0.0000

Data Index: 508092 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.6881. Min Act: 0.0000

Data Index: 781640 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.6908. Min Act: -0.0000

Data Index: 916190 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.6545. Min Act: -0.0000

Data Index: 701223 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.6694. Min Act: -0.0000

Data Index: 644205 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1082517 (C4 (Web Text))

Max Activating Token Index: 185