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

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

Neuron 3046 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.7031. Min Act: -0.0000

Data Index: 266034 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.7937. Min Act: -0.0000

Data Index: 549320 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.4446. Min Act: -0.0000

Data Index: 154066 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.3844. Min Act: -0.0000

Data Index: 103256 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.4658. Min Act: -0.0000

Data Index: 268659 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.0708. Min Act: -0.0000

Data Index: 1023900 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.1859. Min Act: -0.0000

Data Index: 1024626 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.1530. Min Act: -0.0000

Data Index: 118354 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.1170. Min Act: -0.0000

Data Index: 959377 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.2449. Min Act: -0.0000

Data Index: 1267757 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.1993. Min Act: -0.0000

Data Index: 953665 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 3.7937. Min Range: -3.7937

Max Act: 2.8559. Min Act: -0.0000

Data Index: 821687 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 3.7937. Min Range: -3.7937

Max Act: 2.9521. Min Act: -0.0000

Data Index: 782122 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 3.7937. Min Range: -3.7937

Max Act: 2.8760. Min Act: -0.0000

Data Index: 591852 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.1686. Min Act: -0.0000

Data Index: 647615 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 3.7937. Min Range: -3.7937

Max Act: 2.8512. Min Act: 0.0000

Data Index: 1186184 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 3.7937. Min Range: -3.7937

Max Act: 2.8383. Min Act: -0.0000

Data Index: 1208924 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 3.7937. Min Range: -3.7937

Max Act: 2.9419. Min Act: -0.0000

Data Index: 603209 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 3.7937. Min Range: -3.7937

Max Act: 2.7904. Min Act: -0.0000

Data Index: 962936 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 3.7937. Min Range: -3.7937

Max Act: 2.9205. Min Act: -0.0000

Data Index: 544194 (C4 (Web Text))

Max Activating Token Index: 968