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

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

Neuron 5996 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: 1.7446. Min Range: -1.7446

Max Act: 1.7446. Min Act: -0.0000

Data Index: 221525 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.6932. Min Act: -0.0000

Data Index: 1400732 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.5525. Min Act: -0.0000

Data Index: 547600 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.4535. Min Act: -0.0000

Data Index: 1348875 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.4080. Min Act: -0.0000

Data Index: 98665 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.3531. Min Act: -0.0000

Data Index: 1424343 (Python Code)

Max Activating Token Index: 321

Text #6

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.3322. Min Act: -0.0000

Data Index: 1499716 (Python Code)

Max Activating Token Index: 246

Text #7

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.2808. Min Act: -0.0000

Data Index: 321496 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.3127. Min Act: -0.0000

Data Index: 1259856 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1235036 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.2556. Min Act: -0.0000

Data Index: 123727 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.2670. Min Act: -0.0000

Data Index: 712725 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.2543. Min Act: -0.0000

Data Index: 146007 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.2570. Min Act: -0.0000

Data Index: 120193 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.2471. Min Act: -0.0000

Data Index: 1314860 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.3289. Min Act: -0.0000

Data Index: 53737 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.1986. Min Act: -0.0000

Data Index: 1044325 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.2134. Min Act: -0.0000

Data Index: 327180 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.2626. Min Act: -0.0000

Data Index: 1620906 (Python Code)

Max Activating Token Index: 765

Text #19

Max Range: 1.7446. Min Range: -1.7446

Max Act: 1.1708. Min Act: -0.0000

Data Index: 555948 (C4 (Web Text))

Max Activating Token Index: 362