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

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

Neuron 1438 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: 4.5639. Min Range: -4.5639

Max Act: 4.4468. Min Act: -0.0000

Data Index: 1041638 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 4.5639. Min Range: -4.5639

Max Act: 4.5639. Min Act: -0.0000

Data Index: 833459 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 4.5639. Min Range: -4.5639

Max Act: 4.5366. Min Act: -0.0001

Data Index: 615564 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 4.5639. Min Range: -4.5639

Max Act: 4.4556. Min Act: -0.0001

Data Index: 1119013 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 4.5639. Min Range: -4.5639

Max Act: 3.9681. Min Act: -0.0000

Data Index: 885954 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 4.5639. Min Range: -4.5639

Max Act: 3.8481. Min Act: -0.0001

Data Index: 1001963 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 4.5639. Min Range: -4.5639

Max Act: 3.6904. Min Act: -0.0000

Data Index: 457382 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 4.5639. Min Range: -4.5639

Max Act: 3.8287. Min Act: -0.0001

Data Index: 190885 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 4.5639. Min Range: -4.5639

Max Act: 3.8900. Min Act: -0.0001

Data Index: 1289387 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 4.5639. Min Range: -4.5639

Max Act: 4.2439. Min Act: -0.0000

Data Index: 969515 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 4.5639. Min Range: -4.5639

Max Act: 3.7592. Min Act: -0.0000

Data Index: 229191 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 4.5639. Min Range: -4.5639

Max Act: 4.0303. Min Act: -0.0001

Data Index: 1233149 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 4.5639. Min Range: -4.5639

Max Act: 4.1808. Min Act: -0.0001

Data Index: 1147974 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 4.5639. Min Range: -4.5639

Max Act: 3.8875. Min Act: -0.0001

Data Index: 1253473 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 4.5639. Min Range: -4.5639

Max Act: 4.1761. Min Act: -0.0001

Data Index: 60445 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 4.5639. Min Range: -4.5639

Max Act: 3.8105. Min Act: -0.0000

Data Index: 449224 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 4.5639. Min Range: -4.5639

Max Act: 3.4261. Min Act: -0.0000

Data Index: 818779 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 4.5639. Min Range: -4.5639

Max Act: 4.0966. Min Act: -0.0000

Data Index: 904279 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 4.5639. Min Range: -4.5639

Max Act: 3.8015. Min Act: -0.0001

Data Index: 1162429 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 4.5639. Min Range: -4.5639

Max Act: 4.0746. Min Act: -0.0001

Data Index: 115154 (C4 (Web Text))

Max Activating Token Index: 348