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

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

Neuron 1768 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3964. Min Range: -2.3964

Max Act: 2.3964. Min Act: -0.0000

Data Index: 622787 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.5901. Min Act: -0.0000

Data Index: 726032 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1339017 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.2593. Min Act: -0.0000

Data Index: 200114 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.2960. Min Act: -0.0000

Data Index: 94087 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.0719. Min Act: -0.0000

Data Index: 1145744 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.1564. Min Act: -0.0000

Data Index: 1314233 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.1514. Min Act: -0.0000

Data Index: 1054481 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.0696. Min Act: -0.0000

Data Index: 106320 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.1365. Min Act: -0.0000

Data Index: 416623 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.0426. Min Act: -0.0000

Data Index: 552979 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.0486. Min Act: -0.0000

Data Index: 353989 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.0861. Min Act: -0.0000

Data Index: 604460 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.0833. Min Act: -0.0000

Data Index: 494194 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.0188. Min Act: -0.0000

Data Index: 654914 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.1156. Min Act: -0.0000

Data Index: 446334 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 2.3964. Min Range: -2.3964

Max Act: 0.9094. Min Act: -0.0000

Data Index: 269881 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.0287. Min Act: -0.0000

Data Index: 770957 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 2.3964. Min Range: -2.3964

Max Act: 1.0159. Min Act: -0.0000

Data Index: 1225715 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 2.3964. Min Range: -2.3964

Max Act: 0.9411. Min Act: -0.0000

Data Index: 729213 (C4 (Web Text))

Max Activating Token Index: 923