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

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

Neuron 1333 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: 0.0566. Min Range: -0.0566

Max Act: 0.0566. Min Act: -0.0001

Data Index: 908678 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1158099 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1138868 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1137364 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0448. Min Act: -0.0002

Data Index: 35543 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1041709 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0487. Min Act: -0.0001

Data Index: 856419 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1146493 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0466. Min Act: -0.0002

Data Index: 50342 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1309333 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0456. Min Act: -0.0002

Data Index: 31068 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0436. Min Act: -0.0002

Data Index: 943733 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0455. Min Act: -0.0002

Data Index: 17710 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0462. Min Act: -0.0002

Data Index: 882317 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1173152 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1239042 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0427. Min Act: -0.0002

Data Index: 130162 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0423. Min Act: -0.0002

Data Index: 869502 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0420. Min Act: -0.0002

Data Index: 664325 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1225040 (C4 (Web Text))

Max Activating Token Index: 316