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

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

Neuron 1207 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: 0.4969. Min Range: -0.4969

Max Act: 0.4969. Min Act: -0.0001

Data Index: 576435 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4540. Min Act: -0.0001

Data Index: 219980 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4819. Min Act: -0.0001

Data Index: 1206247 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4406. Min Act: -0.0001

Data Index: 77813 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4411. Min Act: -0.0001

Data Index: 598860 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4447. Min Act: -0.0001

Data Index: 363290 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4209. Min Act: -0.0001

Data Index: 547692 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4086. Min Act: -0.0001

Data Index: 514119 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4488. Min Act: -0.0001

Data Index: 1172477 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4330. Min Act: -0.0001

Data Index: 1005594 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3804. Min Act: -0.0001

Data Index: 580656 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3796. Min Act: -0.0001

Data Index: 131685 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3642. Min Act: -0.0001

Data Index: 950340 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3772. Min Act: -0.0001

Data Index: 111743 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3989. Min Act: -0.0001

Data Index: 52717 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3779. Min Act: -0.0001

Data Index: 1261042 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3624. Min Act: -0.0001

Data Index: 112379 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3705. Min Act: -0.0001

Data Index: 899672 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3696. Min Act: -0.0001

Data Index: 552281 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3792. Min Act: -0.0001

Data Index: 53989 (C4 (Web Text))

Max Activating Token Index: 324