Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 767 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.7656. Min Act: -0.0001

Data Index: 322412 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.7326. Min Act: -0.0001

Data Index: 759515 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6454. Min Act: -0.0001

Data Index: 1289437 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6739. Min Act: -0.0001

Data Index: 1342592 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6306. Min Act: -0.0001

Data Index: 1231833 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6052. Min Act: -0.0001

Data Index: 844663 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6374. Min Act: -0.0001

Data Index: 601696 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6165. Min Act: -0.0001

Data Index: 1074845 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6340. Min Act: -0.0001

Data Index: 1080737 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.5885. Min Act: -0.0001

Data Index: 836436 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6129. Min Act: -0.0001

Data Index: 1355363 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.5355. Min Act: -0.0001

Data Index: 469172 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.5700. Min Act: -0.0001

Data Index: 1180560 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.5686. Min Act: -0.0001

Data Index: 321059 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.5512. Min Act: -0.0001

Data Index: 903329 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.5847. Min Act: -0.0001

Data Index: 66825 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.5485. Min Act: -0.0001

Data Index: 379241 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1188903 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.5209. Min Act: -0.0001

Data Index: 266637 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.5708. Min Act: -0.0001

Data Index: 1356529 (C4 (Web Text))

Max Activating Token Index: 405