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

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

Neuron 1845 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.7557. Min Act: -0.0000

Data Index: 1632216 (Python Code)

Max Activating Token Index: 610

Text #1

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1616670 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1594817 (Python Code)

Max Activating Token Index: 124

Text #3

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1604855 (Python Code)

Max Activating Token Index: 858

Text #4

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1471752 (Python Code)

Max Activating Token Index: 434

Text #5

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1650588 (Python Code)

Max Activating Token Index: 140

Text #6

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1607816 (Python Code)

Max Activating Token Index: 872

Text #7

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1617776 (Python Code)

Max Activating Token Index: 131

Text #8

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1649446 (Python Code)

Max Activating Token Index: 373

Text #9

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1535861 (Python Code)

Max Activating Token Index: 111

Text #10

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1395498 (Python Code)

Max Activating Token Index: 996

Text #11

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1591657 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1625877 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1635915 (Python Code)

Max Activating Token Index: 775

Text #14

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1429350 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.3917. Min Act: -0.0000

Data Index: 1500587 (Python Code)

Max Activating Token Index: 777

Text #16

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1604245 (Python Code)

Max Activating Token Index: 421

Text #17

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1549548 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1632761 (Python Code)

Max Activating Token Index: 383

Text #19

Max Range: 0.7557. Min Range: -0.7557

Max Act: 0.3828. Min Act: -0.0000

Data Index: 500716 (C4 (Web Text))

Max Activating Token Index: 824