Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 757 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.3269. Min Act: -0.0000

Data Index: 968538 (The Pile)

Max Activating Token Index: 274

Text #1

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1833521 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1000696 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1394493 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2693. Min Act: -0.0000

Data Index: 112365 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1768132 (The Pile)

Max Activating Token Index: 57

Text #6

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1284685 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1941217 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1208105 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1822104 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2353. Min Act: -0.0000

Data Index: 591368 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1641277 (The Pile)

Max Activating Token Index: 949

Text #12

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2271. Min Act: -0.0000

Data Index: 625782 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2258. Min Act: -0.0000

Data Index: 180181 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1061207 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2151. Min Act: -0.0000

Data Index: 20557 (The Pile)

Max Activating Token Index: 193

Text #16

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1029080 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2204. Min Act: -0.0000

Data Index: 300671 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2085. Min Act: -0.0000

Data Index: 269991 (The Pile)

Max Activating Token Index: 957

Text #19

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1715128 (The Pile)

Max Activating Token Index: 243