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

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

Neuron 2960 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3200. Min Range: -3.3200

Max Act: 3.3200. Min Act: -0.0001

Data Index: 755919 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.7536. Min Act: -0.0000

Data Index: 878845 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.7008. Min Act: -0.0000

Data Index: 481760 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.3412. Min Act: -0.0000

Data Index: 1379825 (Python Code)

Max Activating Token Index: 250

Text #4

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.5399. Min Act: -0.0000

Data Index: 1232906 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.3031. Min Act: -0.0001

Data Index: 755763 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.3646. Min Act: -0.0001

Data Index: 30482 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.1117. Min Act: -0.0000

Data Index: 54459 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.2466. Min Act: -0.0001

Data Index: 1591985 (Python Code)

Max Activating Token Index: 595

Text #9

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.2236. Min Act: -0.0001

Data Index: 624652 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 3.3200. Min Range: -3.3200

Max Act: 1.8829. Min Act: -0.0001

Data Index: 231663 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.3095. Min Act: -0.0001

Data Index: 1413133 (Python Code)

Max Activating Token Index: 990

Text #12

Max Range: 3.3200. Min Range: -3.3200

Max Act: 1.9939. Min Act: -0.0001

Data Index: 762168 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.0784. Min Act: -0.0000

Data Index: 863828 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.0385. Min Act: -0.0000

Data Index: 1116722 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.1231. Min Act: -0.0000

Data Index: 1028211 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 3.3200. Min Range: -3.3200

Max Act: 2.0208. Min Act: -0.0000

Data Index: 423768 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 3.3200. Min Range: -3.3200

Max Act: 1.9937. Min Act: -0.0000

Data Index: 954433 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 3.3200. Min Range: -3.3200

Max Act: 1.9963. Min Act: -0.0000

Data Index: 787181 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 3.3200. Min Range: -3.3200

Max Act: 1.8857. Min Act: -0.0000

Data Index: 153481 (C4 (Web Text))

Max Activating Token Index: 651