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

Dataset: The Pile

Neuron 4010 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0596. Min Range: -3.0596

Max Act: 3.0596. Min Act: -0.0000

Data Index: 164451 (The Pile)

Max Activating Token Index: 405

Text #1

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.0758. Min Act: -0.0000

Data Index: 750236 (The Pile)

Max Activating Token Index: 413

Text #2

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.0664. Min Act: -0.0000

Data Index: 1143452 (The Pile)

Max Activating Token Index: 190

Text #3

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.9804. Min Act: -0.0000

Data Index: 1691926 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.0849. Min Act: -0.0000

Data Index: 100768 (The Pile)

Max Activating Token Index: 890

Text #5

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.8641. Min Act: -0.0000

Data Index: 1756198 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.8370. Min Act: -0.0000

Data Index: 1172988 (The Pile)

Max Activating Token Index: 437

Text #7

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.9322. Min Act: -0.0000

Data Index: 1284783 (The Pile)

Max Activating Token Index: 511

Text #8

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.7734. Min Act: -0.0000

Data Index: 1484398 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.8530. Min Act: -0.0000

Data Index: 1911094 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.8422. Min Act: -0.0000

Data Index: 1496360 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.8203. Min Act: -0.0000

Data Index: 859208 (The Pile)

Max Activating Token Index: 946

Text #12

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.8192. Min Act: -0.0000

Data Index: 1385379 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.6869. Min Act: -0.0000

Data Index: 1513010 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.8687. Min Act: -0.0000

Data Index: 1419612 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.7303. Min Act: -0.0000

Data Index: 1577927 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.7358. Min Act: -0.0000

Data Index: 1533310 (The Pile)

Max Activating Token Index: 50

Text #17

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.8166. Min Act: -0.0000

Data Index: 1082606 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.7184. Min Act: -0.0000

Data Index: 1991444 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 3.0596. Min Range: -3.0596

Max Act: 1.6983. Min Act: -0.0000

Data Index: 171874 (The Pile)

Max Activating Token Index: 307