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

Dataset: The Pile

Neuron 961 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7297. Min Act: -0.0000

Data Index: 1558451 (The Pile)

Max Activating Token Index: 848

Text #1

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.8361. Min Act: -0.0000

Data Index: 1626615 (The Pile)

Max Activating Token Index: 701

Text #2

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.8433. Min Act: -0.0000

Data Index: 307988 (The Pile)

Max Activating Token Index: 211

Text #3

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.6665. Min Act: -0.0000

Data Index: 1066875 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.5740. Min Act: -0.0000

Data Index: 564868 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.4678. Min Act: -0.0000

Data Index: 1534332 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.4356. Min Act: -0.0000

Data Index: 1024739 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.5019. Min Act: -0.0000

Data Index: 785489 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.4133. Min Act: -0.0000

Data Index: 278825 (The Pile)

Max Activating Token Index: 668

Text #9

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.3235. Min Act: -0.0000

Data Index: 509050 (The Pile)

Max Activating Token Index: 113

Text #10

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.4162. Min Act: -0.0000

Data Index: 644511 (The Pile)

Max Activating Token Index: 794

Text #11

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.3997. Min Act: -0.0000

Data Index: 1385548 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.3121. Min Act: -0.0000

Data Index: 493922 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.3171. Min Act: -0.0000

Data Index: 836753 (The Pile)

Max Activating Token Index: 12

Text #14

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.4230. Min Act: -0.0000

Data Index: 1119009 (The Pile)

Max Activating Token Index: 918

Text #15

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.2032. Min Act: -0.0000

Data Index: 1340244 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.3278. Min Act: -0.0000

Data Index: 756700 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.2964. Min Act: -0.0000

Data Index: 1130273 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.2789. Min Act: -0.0000

Data Index: 1188014 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1811774 (The Pile)

Max Activating Token Index: 588