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

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

Neuron 4754 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.7553. Min Act: -0.0000

Data Index: 580447 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5327. Min Act: -0.0000

Data Index: 890538 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5826. Min Act: -0.0000

Data Index: 705776 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5579. Min Act: -0.0000

Data Index: 417979 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5361. Min Act: -0.0000

Data Index: 764231 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5452. Min Act: -0.0000

Data Index: 473919 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1146205 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1220169 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4564. Min Act: -0.0000

Data Index: 81231 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4226. Min Act: -0.0000

Data Index: 237817 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4207. Min Act: -0.0000

Data Index: 659198 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1007824 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.3984. Min Act: -0.0000

Data Index: 511988 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4078. Min Act: -0.0000

Data Index: 348097 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1075328 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.3850. Min Act: -0.0000

Data Index: 765596 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4010. Min Act: -0.0000

Data Index: 516676 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1125759 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.3998. Min Act: -0.0000

Data Index: 549153 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1328257 (C4 (Web Text))

Max Activating Token Index: 748