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

Dataset: The Pile

Neuron 3815 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: 0.8262. Min Range: -0.8262

Max Act: 0.8262. Min Act: -0.0000

Data Index: 378291 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.6235. Min Act: -0.0000

Data Index: 210517 (The Pile)

Max Activating Token Index: 819

Text #2

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1492813 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.6294. Min Act: -0.0000

Data Index: 261312 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1067828 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.6328. Min Act: -0.0000

Data Index: 777837 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1237805 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1673981 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.6235. Min Act: -0.0000

Data Index: 447598 (The Pile)

Max Activating Token Index: 464

Text #9

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1654608 (The Pile)

Max Activating Token Index: 243

Text #10

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.5846. Min Act: -0.0000

Data Index: 193142 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1658065 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.6079. Min Act: -0.0000

Data Index: 290077 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.5357. Min Act: -0.0000

Data Index: 784300 (The Pile)

Max Activating Token Index: 637

Text #14

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1244249 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1038990 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1081893 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.5975. Min Act: -0.0000

Data Index: 964090 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.5584. Min Act: -0.0000

Data Index: 296043 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 0.8262. Min Range: -0.8262

Max Act: 0.5351. Min Act: -0.0000

Data Index: 242562 (The Pile)

Max Activating Token Index: 698