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

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

Neuron 2581 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.7314. Min Act: -0.0002

Data Index: 137918 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.7154. Min Act: -0.0002

Data Index: 775726 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.7069. Min Act: -0.0002

Data Index: 1051560 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6979. Min Act: -0.0002

Data Index: 116045 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6712. Min Act: -0.0002

Data Index: 324640 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6795. Min Act: -0.0002

Data Index: 346174 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6672. Min Act: -0.0002

Data Index: 1173793 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6676. Min Act: -0.0002

Data Index: 1258230 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6627. Min Act: -0.0002

Data Index: 13432 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6518. Min Act: -0.0002

Data Index: 1314793 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6485. Min Act: -0.0002

Data Index: 1358213 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6497. Min Act: -0.0002

Data Index: 77696 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6524. Min Act: -0.0002

Data Index: 528964 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6441. Min Act: -0.0002

Data Index: 423621 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6383. Min Act: -0.0002

Data Index: 1116948 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6523. Min Act: -0.0002

Data Index: 549161 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6464. Min Act: -0.0002

Data Index: 239672 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6444. Min Act: -0.0002

Data Index: 302167 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6290. Min Act: -0.0002

Data Index: 38468 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6393. Min Act: -0.0002

Data Index: 873293 (C4 (Web Text))

Max Activating Token Index: 12