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

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

Neuron 4073 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: 2.3813. Min Range: -2.3813

Max Act: 2.3813. Min Act: -0.0000

Data Index: 234117 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 2.3813. Min Range: -2.3813

Max Act: 2.3271. Min Act: -0.0000

Data Index: 533849 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.8855. Min Act: -0.0000

Data Index: 912796 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.9235. Min Act: -0.0000

Data Index: 1167634 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.8142. Min Act: -0.0000

Data Index: 471284 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.8517. Min Act: -0.0000

Data Index: 894173 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.7263. Min Act: -0.0000

Data Index: 1099762 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.6909. Min Act: -0.0000

Data Index: 794324 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.6822. Min Act: -0.0000

Data Index: 592043 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.7453. Min Act: -0.0000

Data Index: 255069 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.6280. Min Act: -0.0000

Data Index: 1082960 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.6256. Min Act: -0.0000

Data Index: 1023173 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.5896. Min Act: -0.0000

Data Index: 1222651 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.5748. Min Act: -0.0000

Data Index: 202101 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.5673. Min Act: -0.0000

Data Index: 421123 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.5682. Min Act: -0.0000

Data Index: 96719 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.6484. Min Act: -0.0000

Data Index: 394029 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.5161. Min Act: -0.0000

Data Index: 330617 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.5172. Min Act: -0.0000

Data Index: 620313 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 2.3813. Min Range: -2.3813

Max Act: 1.5090. Min Act: 0.0000

Data Index: 662896 (C4 (Web Text))

Max Activating Token Index: 401