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

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

Neuron 105 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4434. Min Act: -0.0001

Data Index: 288802 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4026. Min Act: -0.0001

Data Index: 290569 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4549. Min Act: -0.0001

Data Index: 1257235 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3968. Min Act: -0.0001

Data Index: 692787 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4101. Min Act: -0.0001

Data Index: 1311811 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4055. Min Act: -0.0001

Data Index: 693052 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4050. Min Act: -0.0001

Data Index: 718677 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4026. Min Act: -0.0001

Data Index: 774939 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3822. Min Act: -0.0001

Data Index: 703058 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3833. Min Act: -0.0001

Data Index: 556789 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3807. Min Act: -0.0001

Data Index: 72985 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3738. Min Act: -0.0001

Data Index: 852832 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3889. Min Act: -0.0001

Data Index: 265418 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3634. Min Act: -0.0001

Data Index: 620118 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3573. Min Act: -0.0001

Data Index: 351546 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3642. Min Act: -0.0001

Data Index: 822641 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3475. Min Act: -0.0001

Data Index: 232465 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3823. Min Act: -0.0001

Data Index: 791090 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3358. Min Act: -0.0001

Data Index: 93932 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3666. Min Act: -0.0001

Data Index: 107256 (C4 (Web Text))

Max Activating Token Index: 8