Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3322 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.3718. Min Act: -0.0001

Data Index: 52267 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.0864. Min Act: -0.0000

Data Index: 962183 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.0091. Min Act: -0.0001

Data Index: 231617 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.4808. Min Act: -0.0001

Data Index: 1252683 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.9674. Min Act: -0.0001

Data Index: 357599 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.7868. Min Act: -0.0000

Data Index: 966347 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.2757. Min Act: -0.0000

Data Index: 27245 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.9327. Min Act: -0.0001

Data Index: 242157 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.8409. Min Act: -0.0001

Data Index: 354268 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.3959. Min Act: -0.0001

Data Index: 274221 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.6972. Min Act: -0.0000

Data Index: 521051 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.3364. Min Act: -0.0001

Data Index: 1335796 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.0080. Min Act: -0.0001

Data Index: 156634 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.4551. Min Act: -0.0000

Data Index: 874167 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.2823. Min Act: -0.0001

Data Index: 841356 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.4554. Min Act: -0.0001

Data Index: 834507 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.7489. Min Act: -0.0000

Data Index: 1075126 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.7528. Min Act: -0.0001

Data Index: 1098271 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.3803. Min Act: -0.0001

Data Index: 481288 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.5065. Min Act: -0.0000

Data Index: 405993 (C4 (Web Text))

Max Activating Token Index: 320