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

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

Neuron 3645 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5435. Min Range: -1.5435

Max Act: 1.5435. Min Act: -0.0000

Data Index: 1213565 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.5435. Min Range: -1.5435

Max Act: 1.3117. Min Act: -0.0000

Data Index: 532680 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 1.5435. Min Range: -1.5435

Max Act: 1.0898. Min Act: -0.0000

Data Index: 716847 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.8949. Min Act: -0.0000

Data Index: 537308 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.8881. Min Act: 0.0000

Data Index: 1026391 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1019429 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1075195 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1323578 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1171555 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.7979. Min Act: -0.0000

Data Index: 435657 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1122922 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.8249. Min Act: -0.0000

Data Index: 387367 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.7245. Min Act: -0.0000

Data Index: 120673 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1180535 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.7731. Min Act: -0.0000

Data Index: 889700 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.8152. Min Act: -0.0000

Data Index: 744232 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.7599. Min Act: -0.0000

Data Index: 8894 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.7052. Min Act: -0.0000

Data Index: 343843 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.7037. Min Act: -0.0000

Data Index: 670091 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 1.5435. Min Range: -1.5435

Max Act: 0.6951. Min Act: -0.0000

Data Index: 994833 (C4 (Web Text))

Max Activating Token Index: 187