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

Dataset: The Pile

Neuron 3295 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5964. Min Range: -3.5964

Max Act: 3.4852. Min Act: -0.0000

Data Index: 1638096 (The Pile)

Max Activating Token Index: 159

Text #1

Max Range: 3.5964. Min Range: -3.5964

Max Act: 3.5964. Min Act: -0.0000

Data Index: 21610 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 3.5964. Min Range: -3.5964

Max Act: 3.3676. Min Act: -0.0000

Data Index: 1037786 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 3.5964. Min Range: -3.5964

Max Act: 3.3468. Min Act: -0.0000

Data Index: 220824 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 3.5964. Min Range: -3.5964

Max Act: 3.2077. Min Act: -0.0000

Data Index: 965131 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 3.5964. Min Range: -3.5964

Max Act: 3.1230. Min Act: -0.0000

Data Index: 1196485 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 3.5964. Min Range: -3.5964

Max Act: 3.0132. Min Act: -0.0000

Data Index: 1541921 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 3.5964. Min Range: -3.5964

Max Act: 3.1203. Min Act: -0.0000

Data Index: 953237 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 3.5964. Min Range: -3.5964

Max Act: 3.0506. Min Act: -0.0000

Data Index: 1565016 (The Pile)

Max Activating Token Index: 384

Text #9

Max Range: 3.5964. Min Range: -3.5964

Max Act: 3.0280. Min Act: -0.0000

Data Index: 1046826 (The Pile)

Max Activating Token Index: 436

Text #10

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.7665. Min Act: -0.0000

Data Index: 806619 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 3.5964. Min Range: -3.5964

Max Act: 3.1299. Min Act: -0.0000

Data Index: 329560 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.9527. Min Act: -0.0000

Data Index: 1029875 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.9357. Min Act: -0.0000

Data Index: 11126 (The Pile)

Max Activating Token Index: 447

Text #14

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.9501. Min Act: -0.0000

Data Index: 780208 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.9267. Min Act: -0.0000

Data Index: 1531376 (The Pile)

Max Activating Token Index: 618

Text #16

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.9462. Min Act: -0.0000

Data Index: 404599 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.6232. Min Act: -0.0000

Data Index: 261614 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.8121. Min Act: -0.0000

Data Index: 1612954 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.7226. Min Act: -0.0000

Data Index: 737513 (The Pile)

Max Activating Token Index: 218