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

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

Neuron 1054 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0578. Min Act: -0.0004

Data Index: 973674 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0559. Min Act: -0.0004

Data Index: 1287116 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0512. Min Act: -0.0004

Data Index: 657750 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0498. Min Act: -0.0004

Data Index: 60985 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0506. Min Act: -0.0004

Data Index: 1195951 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0482. Min Act: -0.0004

Data Index: 1135225 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0478. Min Act: -0.0004

Data Index: 967191 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0494. Min Act: -0.0004

Data Index: 406957 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0466. Min Act: -0.0004

Data Index: 629251 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0466. Min Act: -0.0004

Data Index: 735809 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0462. Min Act: -0.0004

Data Index: 316344 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0402. Min Act: -0.0004

Data Index: 718871 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0439. Min Act: -0.0004

Data Index: 827361 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0434. Min Act: -0.0004

Data Index: 726519 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0451. Min Act: -0.0004

Data Index: 608085 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0448. Min Act: -0.0004

Data Index: 540472 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0468. Min Act: -0.0004

Data Index: 1296497 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0449. Min Act: -0.0004

Data Index: 322551 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0463. Min Act: -0.0004

Data Index: 1000650 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0462. Min Act: -0.0004

Data Index: 259140 (C4 (Web Text))

Max Activating Token Index: 173