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

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

Neuron 1065 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.5922. Min Act: -0.0000

Data Index: 625153 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.4411. Min Act: -0.0000

Data Index: 858266 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2637. Min Act: -0.0000

Data Index: 1119642 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.3123. Min Act: -0.0000

Data Index: 1340417 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1065543 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1045364 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1905. Min Act: -0.0000

Data Index: 561421 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1719. Min Act: -0.0000

Data Index: 307604 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2300. Min Act: -0.0000

Data Index: 408764 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1204. Min Act: -0.0000

Data Index: 183285 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1461. Min Act: -0.0000

Data Index: 42953 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1118543 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1078. Min Act: -0.0000

Data Index: 258657 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0240. Min Act: -0.0000

Data Index: 78333 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0996. Min Act: -0.0000

Data Index: 829618 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0368. Min Act: -0.0000

Data Index: 788402 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1255923 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.9649. Min Act: -0.0000

Data Index: 81801 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1255995 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1343162 (C4 (Web Text))

Max Activating Token Index: 986