Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 622 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1945878 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6915. Min Act: -0.0001

Data Index: 1578632 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1775980 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6027. Min Act: -0.0001

Data Index: 98543 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1051708 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6385. Min Act: -0.0001

Data Index: 1073793 (The Pile)

Max Activating Token Index: 182

Text #6

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6156. Min Act: -0.0001

Data Index: 819860 (The Pile)

Max Activating Token Index: 387

Text #7

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6142. Min Act: -0.0001

Data Index: 269722 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6119. Min Act: -0.0001

Data Index: 1004058 (The Pile)

Max Activating Token Index: 339

Text #9

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1493062 (The Pile)

Max Activating Token Index: 160

Text #10

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5810. Min Act: -0.0000

Data Index: 57496 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1490671 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1997103 (The Pile)

Max Activating Token Index: 417

Text #13

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6172. Min Act: -0.0000

Data Index: 77157 (The Pile)

Max Activating Token Index: 303

Text #14

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5597. Min Act: -0.0001

Data Index: 676028 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5882. Min Act: -0.0000

Data Index: 846726 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5622. Min Act: -0.0000

Data Index: 101268 (The Pile)

Max Activating Token Index: 728

Text #17

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5939. Min Act: -0.0001

Data Index: 366939 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5930. Min Act: -0.0001

Data Index: 650579 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1661348 (The Pile)

Max Activating Token Index: 772