Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 275 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0865. Min Range: -2.0865

Max Act: 2.0865. Min Act: -0.0000

Data Index: 891375 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.5383. Min Act: -0.0000

Data Index: 814287 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.6617. Min Act: -0.0000

Data Index: 784515 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.4617. Min Act: -0.0000

Data Index: 806979 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.4012. Min Act: -0.0000

Data Index: 276507 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.2751. Min Act: -0.0000

Data Index: 615144 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.3510. Min Act: -0.0000

Data Index: 1185922 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.2696. Min Act: -0.0001

Data Index: 142419 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.2303. Min Act: -0.0000

Data Index: 62876 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.2515. Min Act: -0.0000

Data Index: 82380 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.2372. Min Act: -0.0000

Data Index: 934361 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.1670. Min Act: 0.0000

Data Index: 340385 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.2321. Min Act: -0.0000

Data Index: 977796 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.1870. Min Act: -0.0000

Data Index: 200306 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.1452. Min Act: -0.0000

Data Index: 213459 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.1012. Min Act: -0.0001

Data Index: 636723 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.1010. Min Act: 0.0000

Data Index: 835110 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1041214 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.1956. Min Act: -0.0000

Data Index: 76794 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 2.0865. Min Range: -2.0865

Max Act: 1.1555. Min Act: -0.0000

Data Index: 926696 (C4 (Web Text))

Max Activating Token Index: 873