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

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

Neuron 1706 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4660. Min Act: -0.0001

Data Index: 713527 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4387. Min Act: -0.0001

Data Index: 827105 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4495. Min Act: -0.0001

Data Index: 450794 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4085. Min Act: -0.0001

Data Index: 276183 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3914. Min Act: -0.0001

Data Index: 1345371 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4058. Min Act: -0.0001

Data Index: 934379 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4299. Min Act: -0.0001

Data Index: 1253692 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3897. Min Act: -0.0001

Data Index: 797261 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3872. Min Act: -0.0001

Data Index: 1020981 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3832. Min Act: -0.0001

Data Index: 1236362 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3882. Min Act: -0.0001

Data Index: 650070 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3718. Min Act: -0.0001

Data Index: 1218925 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3649. Min Act: -0.0001

Data Index: 635448 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3636. Min Act: -0.0001

Data Index: 801170 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3601. Min Act: -0.0001

Data Index: 343933 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3501. Min Act: -0.0001

Data Index: 487369 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3597. Min Act: -0.0001

Data Index: 167197 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3592. Min Act: -0.0001

Data Index: 9085 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3634. Min Act: -0.0001

Data Index: 354695 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3524. Min Act: -0.0001

Data Index: 252353 (C4 (Web Text))

Max Activating Token Index: 202