Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 144 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0626. Min Act: -0.0002

Data Index: 911063 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0582. Min Act: -0.0002

Data Index: 969275 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0611. Min Act: -0.0002

Data Index: 263787 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1378459 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0583. Min Act: -0.0002

Data Index: 869452 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0600. Min Act: -0.0002

Data Index: 272923 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1061318 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0534. Min Act: -0.0002

Data Index: 762052 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1381678 (Python Code)

Max Activating Token Index: 633

Text #9

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0568. Min Act: -0.0002

Data Index: 874492 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0559. Min Act: -0.0002

Data Index: 123411 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1267710 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1259832 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0550. Min Act: -0.0002

Data Index: 869731 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1556833 (Python Code)

Max Activating Token Index: 441

Text #15

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0538. Min Act: -0.0002

Data Index: 259989 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0568. Min Act: -0.0002

Data Index: 735736 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0554. Min Act: -0.0002

Data Index: 265460 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1335392 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1535138 (Python Code)

Max Activating Token Index: 521