Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1649 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1285998 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0124. Min Act: -0.0006

Data Index: 73830 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0124. Min Act: -0.0006

Data Index: 209853 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0124. Min Act: -0.0006

Data Index: 705688 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0123. Min Act: -0.0006

Data Index: 620627 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0124. Min Act: -0.0006

Data Index: 186995 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0123. Min Act: -0.0006

Data Index: 6260 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0123. Min Act: -0.0006

Data Index: 67694 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0123. Min Act: -0.0006

Data Index: 220654 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0124. Min Act: -0.0006

Data Index: 749143 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1187427 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1276387 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0006

Data Index: 96076 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0121. Min Act: -0.0006

Data Index: 762534 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1460415 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0006

Data Index: 655290 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0006

Data Index: 671888 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0006

Data Index: 148841 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1222440 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0006

Data Index: 46499 (C4 (Web Text))

Max Activating Token Index: 608