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

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

Neuron 4974 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.7761. Min Act: -0.0001

Data Index: 282704 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.7555. Min Act: -0.0001

Data Index: 889769 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.8001. Min Act: -0.0001

Data Index: 825568 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6887. Min Act: -0.0001

Data Index: 1144633 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6923. Min Act: -0.0001

Data Index: 1027411 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6510. Min Act: -0.0001

Data Index: 1046187 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6581. Min Act: -0.0001

Data Index: 1355793 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6023. Min Act: -0.0001

Data Index: 519513 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6461. Min Act: -0.0001

Data Index: 765283 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6136. Min Act: -0.0001

Data Index: 250323 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5550. Min Act: -0.0001

Data Index: 1163443 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5712. Min Act: -0.0001

Data Index: 672314 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5730. Min Act: -0.0001

Data Index: 626525 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5787. Min Act: -0.0001

Data Index: 723343 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5736. Min Act: -0.0001

Data Index: 920970 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5355. Min Act: -0.0001

Data Index: 847158 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6010. Min Act: -0.0001

Data Index: 1325119 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5473. Min Act: -0.0001

Data Index: 818268 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5734. Min Act: -0.0001

Data Index: 780282 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5738. Min Act: -0.0001

Data Index: 227503 (C4 (Web Text))

Max Activating Token Index: 35