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

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

Neuron 2116 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7097. Min Range: -4.7097

Max Act: 4.7097. Min Act: -0.0000

Data Index: 622507 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 4.7097. Min Range: -4.7097

Max Act: 4.5978. Min Act: -0.0000

Data Index: 374536 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 4.7097. Min Range: -4.7097

Max Act: 4.2427. Min Act: -0.0000

Data Index: 573409 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.8227. Min Act: -0.0000

Data Index: 341330 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.6505. Min Act: -0.0000

Data Index: 234843 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.5320. Min Act: -0.0000

Data Index: 133086 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.6977. Min Act: -0.0000

Data Index: 373716 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.2591. Min Act: -0.0000

Data Index: 1013802 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.3174. Min Act: -0.0000

Data Index: 1258035 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.2661. Min Act: -0.0000

Data Index: 445590 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.5681. Min Act: -0.0000

Data Index: 230358 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.1714. Min Act: -0.0000

Data Index: 928793 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.3342. Min Act: -0.0000

Data Index: 6174 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.4635. Min Act: -0.0000

Data Index: 681472 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.3269. Min Act: -0.0000

Data Index: 138693 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.1883. Min Act: -0.0000

Data Index: 727892 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.1862. Min Act: -0.0000

Data Index: 99045 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.2921. Min Act: -0.0000

Data Index: 39904 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.0197. Min Act: -0.0000

Data Index: 494431 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 4.7097. Min Range: -4.7097

Max Act: 3.2725. Min Act: -0.0000

Data Index: 922123 (C4 (Web Text))

Max Activating Token Index: 810