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

Dataset: The Pile

Neuron 2075 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: 1.2080. Min Range: -1.2080

Max Act: 1.2080. Min Act: -0.0000

Data Index: 886809 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 1.2080. Min Range: -1.2080

Max Act: 1.0580. Min Act: -0.0000

Data Index: 351656 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 1.2080. Min Range: -1.2080

Max Act: 1.0891. Min Act: -0.0000

Data Index: 705479 (The Pile)

Max Activating Token Index: 670

Text #3

Max Range: 1.2080. Min Range: -1.2080

Max Act: 1.0504. Min Act: -0.0000

Data Index: 484804 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.9837. Min Act: -0.0000

Data Index: 793561 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.9781. Min Act: -0.0000

Data Index: 532617 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1785845 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.9700. Min Act: -0.0000

Data Index: 764471 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1966617 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.9163. Min Act: -0.0000

Data Index: 163231 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1931731 (The Pile)

Max Activating Token Index: 266

Text #11

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1182863 (The Pile)

Max Activating Token Index: 335

Text #12

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.8873. Min Act: -0.0000

Data Index: 565604 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.8864. Min Act: -0.0000

Data Index: 753199 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1178022 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.8999. Min Act: -0.0000

Data Index: 358574 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.8765. Min Act: 0.0000

Data Index: 1452008 (The Pile)

Max Activating Token Index: 266

Text #17

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1055866 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.8181. Min Act: -0.0000

Data Index: 105804 (The Pile)

Max Activating Token Index: 975

Text #19

Max Range: 1.2080. Min Range: -1.2080

Max Act: 0.8504. Min Act: -0.0000

Data Index: 848253 (The Pile)

Max Activating Token Index: 263