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

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

Neuron 2077 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1510819 (Python Code)

Max Activating Token Index: 197

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1592810 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0780. Min Act: -0.0001

Data Index: 9228 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1622255 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0758. Min Act: -0.0001

Data Index: 45153 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0741. Min Act: -0.0001

Data Index: 4555 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0686. Min Act: -0.0001

Data Index: 378051 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1153977 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0677. Min Act: -0.0001

Data Index: 225365 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0661. Min Act: -0.0001

Data Index: 710739 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0654. Min Act: -0.0001

Data Index: 386039 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1622927 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0667. Min Act: -0.0001

Data Index: 216320 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1033575 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1571128 (Python Code)

Max Activating Token Index: 492

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0631. Min Act: -0.0001

Data Index: 980783 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0611. Min Act: -0.0001

Data Index: 205495 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0689. Min Act: -0.0001

Data Index: 973646 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1558332 (Python Code)

Max Activating Token Index: 805

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0572. Min Act: -0.0001

Data Index: 992182 (C4 (Web Text))

Max Activating Token Index: 60