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

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

Neuron 394 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: 0.6890. Min Range: -0.6890

Max Act: 0.6890. Min Act: -0.0001

Data Index: 398594 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5855. Min Act: -0.0001

Data Index: 852623 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5420. Min Act: -0.0001

Data Index: 19934 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5235. Min Act: -0.0001

Data Index: 638102 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4766. Min Act: -0.0001

Data Index: 326413 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4683. Min Act: -0.0001

Data Index: 628621 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4811. Min Act: -0.0001

Data Index: 423472 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4783. Min Act: -0.0001

Data Index: 1191078 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4718. Min Act: -0.0001

Data Index: 557076 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4942. Min Act: -0.0001

Data Index: 906065 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4722. Min Act: -0.0001

Data Index: 1132688 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4555. Min Act: -0.0001

Data Index: 739716 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4393. Min Act: -0.0001

Data Index: 1283499 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4561. Min Act: -0.0001

Data Index: 107651 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4398. Min Act: -0.0001

Data Index: 1359204 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4553. Min Act: -0.0001

Data Index: 1110657 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4649. Min Act: -0.0001

Data Index: 144298 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4301. Min Act: -0.0001

Data Index: 550005 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4440. Min Act: -0.0001

Data Index: 1075159 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4277. Min Act: -0.0001

Data Index: 1087612 (C4 (Web Text))

Max Activating Token Index: 923