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

Dataset: The Pile

Neuron 3962 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1755407 (The Pile)

Max Activating Token Index: 342

Text #1

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1697647 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1548862 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6403. Min Act: -0.0000

Data Index: 696077 (The Pile)

Max Activating Token Index: 532

Text #4

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6798. Min Act: -0.0000

Data Index: 64137 (The Pile)

Max Activating Token Index: 699

Text #5

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6337. Min Act: -0.0000

Data Index: 623123 (The Pile)

Max Activating Token Index: 396

Text #6

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6245. Min Act: -0.0000

Data Index: 25528 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6604. Min Act: -0.0000

Data Index: 172995 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5919. Min Act: -0.0000

Data Index: 155325 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5984. Min Act: -0.0000

Data Index: 900828 (The Pile)

Max Activating Token Index: 501

Text #10

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6277. Min Act: 0.0000

Data Index: 1065909 (The Pile)

Max Activating Token Index: 184

Text #11

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6110. Min Act: -0.0000

Data Index: 148983 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6316. Min Act: -0.0000

Data Index: 202299 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6453. Min Act: -0.0000

Data Index: 293433 (The Pile)

Max Activating Token Index: 574

Text #14

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6554. Min Act: 0.0000

Data Index: 1446403 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1257295 (The Pile)

Max Activating Token Index: 794

Text #16

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6108. Min Act: -0.0000

Data Index: 988807 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6177. Min Act: 0.0000

Data Index: 1537193 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5966. Min Act: -0.0000

Data Index: 564241 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5835. Min Act: -0.0000

Data Index: 437100 (The Pile)

Max Activating Token Index: 514