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

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

Neuron 876 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: 1.9650. Min Range: -1.9650

Max Act: 1.9650. Min Act: -0.0001

Data Index: 1575225 (Python Code)

Max Activating Token Index: 169

Text #1

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.8093. Min Act: -0.0001

Data Index: 1573383 (Python Code)

Max Activating Token Index: 708

Text #2

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.8666. Min Act: -0.0001

Data Index: 21263 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.6871. Min Act: -0.0001

Data Index: 1534327 (Python Code)

Max Activating Token Index: 276

Text #4

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.8591. Min Act: -0.0001

Data Index: 998009 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7735. Min Act: -0.0001

Data Index: 1603273 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.6745. Min Act: -0.0001

Data Index: 74927 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7142. Min Act: -0.0001

Data Index: 1362646 (Python Code)

Max Activating Token Index: 530

Text #8

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7787. Min Act: -0.0001

Data Index: 1406191 (Python Code)

Max Activating Token Index: 567

Text #9

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.6868. Min Act: -0.0001

Data Index: 1594182 (Python Code)

Max Activating Token Index: 776

Text #10

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.6687. Min Act: -0.0001

Data Index: 1485594 (Python Code)

Max Activating Token Index: 619

Text #11

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7460. Min Act: -0.0001

Data Index: 956606 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7552. Min Act: -0.0001

Data Index: 1632713 (Python Code)

Max Activating Token Index: 552

Text #13

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7908. Min Act: -0.0001

Data Index: 114118 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7406. Min Act: -0.0001

Data Index: 1270960 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.6904. Min Act: -0.0001

Data Index: 1640849 (Python Code)

Max Activating Token Index: 446

Text #16

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.6535. Min Act: -0.0001

Data Index: 663004 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7886. Min Act: -0.0001

Data Index: 1155287 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.5767. Min Act: -0.0001

Data Index: 1604831 (Python Code)

Max Activating Token Index: 718

Text #19

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7214. Min Act: -0.0001

Data Index: 415881 (C4 (Web Text))

Max Activating Token Index: 448