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

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

Neuron 5602 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: 2.0389. Min Range: -2.0389

Max Act: 2.0389. Min Act: -0.0000

Data Index: 425769 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 2.0389. Min Range: -2.0389

Max Act: 2.0296. Min Act: -0.0000

Data Index: 958635 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 2.0389. Min Range: -2.0389

Max Act: 2.0303. Min Act: -0.0001

Data Index: 528505 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.6522. Min Act: -0.0001

Data Index: 764682 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.7048. Min Act: -0.0000

Data Index: 152527 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.7948. Min Act: -0.0000

Data Index: 202638 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.9607. Min Act: -0.0001

Data Index: 1030001 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.3978. Min Act: -0.0000

Data Index: 1543398 (Python Code)

Max Activating Token Index: 322

Text #8

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.4418. Min Act: -0.0000

Data Index: 718198 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.4597. Min Act: -0.0001

Data Index: 1559441 (Python Code)

Max Activating Token Index: 533

Text #10

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.5429. Min Act: -0.0000

Data Index: 1498719 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.4168. Min Act: -0.0000

Data Index: 1374514 (Python Code)

Max Activating Token Index: 548

Text #12

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.5679. Min Act: -0.0001

Data Index: 284918 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.5103. Min Act: -0.0001

Data Index: 49770 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.4461. Min Act: -0.0000

Data Index: 1650696 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1377955 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.3687. Min Act: -0.0000

Data Index: 1422210 (Python Code)

Max Activating Token Index: 460

Text #17

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.2974. Min Act: -0.0000

Data Index: 365435 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1560955 (Python Code)

Max Activating Token Index: 735

Text #19

Max Range: 2.0389. Min Range: -2.0389

Max Act: 1.3488. Min Act: -0.0001

Data Index: 270699 (C4 (Web Text))

Max Activating Token Index: 634