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

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

Neuron 6003 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.8595. Min Act: -0.0000

Data Index: 814303 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.8337. Min Act: -0.0001

Data Index: 27204 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.8019. Min Act: -0.0000

Data Index: 592515 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.7816. Min Act: -0.0001

Data Index: 78382 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.8030. Min Act: -0.0001

Data Index: 813576 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.7953. Min Act: -0.0000

Data Index: 1226768 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.1779. Min Act: -0.0001

Data Index: 57279 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.4403. Min Act: -0.0001

Data Index: 1067625 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.5520. Min Act: -0.0000

Data Index: 507499 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.4144. Min Act: -0.0000

Data Index: 9575 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.4062. Min Act: -0.0001

Data Index: 138189 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.5551. Min Act: -0.0001

Data Index: 779643 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.3742. Min Act: -0.0001

Data Index: 1195622 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.5391. Min Act: -0.0000

Data Index: 675314 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.3574. Min Act: -0.0001

Data Index: 703683 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.9852. Min Act: -0.0000

Data Index: 784136 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.4853. Min Act: -0.0000

Data Index: 346858 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.3485. Min Act: -0.0001

Data Index: 388384 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.4881. Min Act: -0.0001

Data Index: 754826 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 3.9852. Min Range: -3.9852

Max Act: 3.3296. Min Act: -0.0000

Data Index: 1082660 (C4 (Web Text))

Max Activating Token Index: 435