Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1188 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1564344 (Python Code)

Max Activating Token Index: 528

Text #1

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0657. Min Act: -0.0003

Data Index: 304385 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0610. Min Act: -0.0003

Data Index: 564305 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1026206 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1631149 (Python Code)

Max Activating Token Index: 658

Text #5

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1015451 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0585. Min Act: -0.0003

Data Index: 464768 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0574. Min Act: -0.0003

Data Index: 127549 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1104797 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1439839 (Python Code)

Max Activating Token Index: 67

Text #10

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1220109 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0567. Min Act: -0.0003

Data Index: 972941 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0563. Min Act: -0.0003

Data Index: 631886 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1420183 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1056681 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0535. Min Act: -0.0004

Data Index: 1289203 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1082303 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1308998 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0551. Min Act: -0.0003

Data Index: 51646 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0533. Min Act: -0.0003

Data Index: 981164 (C4 (Web Text))

Max Activating Token Index: 1005