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

Dataset: The Pile

Neuron 4123 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5763. Min Act: -0.0000

Data Index: 671565 (The Pile)

Max Activating Token Index: 294

Text #1

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5930. Min Act: -0.0000

Data Index: 582880 (The Pile)

Max Activating Token Index: 327

Text #2

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.6026. Min Act: -0.0000

Data Index: 289530 (The Pile)

Max Activating Token Index: 23

Text #3

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1426152 (The Pile)

Max Activating Token Index: 727

Text #4

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5538. Min Act: -0.0000

Data Index: 165766 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5372. Min Act: -0.0000

Data Index: 825474 (The Pile)

Max Activating Token Index: 548

Text #6

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5160. Min Act: -0.0000

Data Index: 516542 (The Pile)

Max Activating Token Index: 810

Text #7

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1295702 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1701529 (The Pile)

Max Activating Token Index: 270

Text #9

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5254. Min Act: -0.0000

Data Index: 261306 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5219. Min Act: -0.0000

Data Index: 371940 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4874. Min Act: -0.0000

Data Index: 341617 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5353. Min Act: -0.0000

Data Index: 242302 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5144. Min Act: -0.0000

Data Index: 24357 (The Pile)

Max Activating Token Index: 793

Text #14

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4805. Min Act: -0.0000

Data Index: 876529 (The Pile)

Max Activating Token Index: 380

Text #15

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1820248 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5223. Min Act: -0.0000

Data Index: 823919 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1098538 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1054242 (The Pile)

Max Activating Token Index: 38

Text #19

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4782. Min Act: -0.0000

Data Index: 483520 (The Pile)

Max Activating Token Index: 978