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

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

Neuron 3619 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.8500. Min Act: -0.0000

Data Index: 813842 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.8075. Min Act: -0.0000

Data Index: 1280674 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.7364. Min Act: -0.0000

Data Index: 925097 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.7445. Min Act: -0.0000

Data Index: 672823 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.5708. Min Act: -0.0000

Data Index: 931144 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.6953. Min Act: -0.0000

Data Index: 998779 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.6367. Min Act: -0.0000

Data Index: 497120 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.6233. Min Act: -0.0000

Data Index: 801376 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.6104. Min Act: -0.0000

Data Index: 673165 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.7547. Min Act: -0.0000

Data Index: 869214 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.7491. Min Act: -0.0000

Data Index: 95827 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.7347. Min Act: -0.0000

Data Index: 155257 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.5916. Min Act: -0.0000

Data Index: 1312712 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.5815. Min Act: -0.0000

Data Index: 1248052 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.5834. Min Act: -0.0000

Data Index: 959971 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.4617. Min Act: -0.0000

Data Index: 752864 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.6948. Min Act: -0.0000

Data Index: 171427 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.4261. Min Act: -0.0000

Data Index: 312855 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.5440. Min Act: -0.0000

Data Index: 916584 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 2.8500. Min Range: -2.8500

Max Act: 2.5606. Min Act: -0.0000

Data Index: 419235 (C4 (Web Text))

Max Activating Token Index: 935