Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 366 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4712. Min Act: -0.0001

Data Index: 818066 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3984. Min Act: -0.0001

Data Index: 717312 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4688. Min Act: -0.0001

Data Index: 180387 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3959. Min Act: -0.0001

Data Index: 281377 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4583. Min Act: -0.0001

Data Index: 483577 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4460. Min Act: -0.0001

Data Index: 1310922 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4254. Min Act: -0.0001

Data Index: 416865 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3696. Min Act: -0.0001

Data Index: 78682 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3108. Min Act: -0.0001

Data Index: 1185150 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4097. Min Act: -0.0001

Data Index: 891109 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3838. Min Act: -0.0001

Data Index: 760090 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3266. Min Act: -0.0001

Data Index: 529244 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4002. Min Act: -0.0001

Data Index: 114209 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3895. Min Act: -0.0001

Data Index: 686415 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3820. Min Act: -0.0001

Data Index: 109096 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3476. Min Act: -0.0001

Data Index: 659661 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3862. Min Act: -0.0001

Data Index: 561150 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4024. Min Act: -0.0001

Data Index: 926894 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3901. Min Act: -0.0001

Data Index: 1108070 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3869. Min Act: -0.0001

Data Index: 181751 (C4 (Web Text))

Max Activating Token Index: 880