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

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

Neuron 2037 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0843. Min Act: -0.0000

Data Index: 499925 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.8860. Min Act: -0.0000

Data Index: 1056335 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.8790. Min Act: -0.0000

Data Index: 154650 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.3561. Min Act: -0.0000

Data Index: 893125 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.4907. Min Act: -0.0000

Data Index: 104438 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.3245. Min Act: -0.0000

Data Index: 444986 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 4.0843. Min Range: -4.0843

Max Act: 2.9914. Min Act: -0.0000

Data Index: 1181775 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.3759. Min Act: -0.0000

Data Index: 1152354 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.2276. Min Act: -0.0000

Data Index: 742914 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.0041. Min Act: -0.0000

Data Index: 1196107 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.1581. Min Act: -0.0000

Data Index: 229963 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 4.0843. Min Range: -4.0843

Max Act: 2.9802. Min Act: -0.0000

Data Index: 665561 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 4.0843. Min Range: -4.0843

Max Act: 2.6952. Min Act: -0.0000

Data Index: 480474 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 4.0843. Min Range: -4.0843

Max Act: 2.9554. Min Act: -0.0000

Data Index: 471401 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 4.0843. Min Range: -4.0843

Max Act: 2.8324. Min Act: -0.0000

Data Index: 778184 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 4.0843. Min Range: -4.0843

Max Act: 2.9523. Min Act: -0.0000

Data Index: 600263 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 4.0843. Min Range: -4.0843

Max Act: 2.8049. Min Act: -0.0000

Data Index: 429991 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 4.0843. Min Range: -4.0843

Max Act: 2.9056. Min Act: -0.0000

Data Index: 126423 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.0496. Min Act: -0.0000

Data Index: 468025 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 4.0843. Min Range: -4.0843

Max Act: 2.8907. Min Act: -0.0000

Data Index: 460527 (C4 (Web Text))

Max Activating Token Index: 80