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

Dataset: The Pile

Neuron 370 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1668987 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1697951 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1281084 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3833. Min Act: -0.0000

Data Index: 455218 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4139. Min Act: -0.0000

Data Index: 401867 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1303300 (The Pile)

Max Activating Token Index: 134

Text #6

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1910067 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3586. Min Act: -0.0000

Data Index: 803477 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3314. Min Act: -0.0000

Data Index: 858097 (The Pile)

Max Activating Token Index: 152

Text #9

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3198. Min Act: -0.0000

Data Index: 849239 (The Pile)

Max Activating Token Index: 825

Text #10

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3480. Min Act: -0.0000

Data Index: 780825 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3287. Min Act: -0.0000

Data Index: 984217 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1644187 (The Pile)

Max Activating Token Index: 797

Text #13

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3354. Min Act: -0.0000

Data Index: 295461 (The Pile)

Max Activating Token Index: 793

Text #14

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1008588 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.2806. Min Act: -0.0000

Data Index: 1595595 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.2958. Min Act: -0.0000

Data Index: 906720 (The Pile)

Max Activating Token Index: 734

Text #17

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3120. Min Act: -0.0000

Data Index: 6790 (The Pile)

Max Activating Token Index: 591

Text #18

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1262056 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3066. Min Act: -0.0000

Data Index: 302124 (The Pile)

Max Activating Token Index: 38