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

Dataset: The Pile

Neuron 2163 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: 1.6400. Min Range: -1.6400

Max Act: 1.6400. Min Act: -0.0001

Data Index: 1720284 (The Pile)

Max Activating Token Index: 594

Text #1

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.4670. Min Act: -0.0000

Data Index: 1778564 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.6226. Min Act: -0.0000

Data Index: 1276554 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.4146. Min Act: -0.0000

Data Index: 1028721 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.2817. Min Act: -0.0000

Data Index: 771945 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.4122. Min Act: -0.0000

Data Index: 765377 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1364224 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.3759. Min Act: -0.0000

Data Index: 547201 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.3655. Min Act: -0.0000

Data Index: 161101 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.3445. Min Act: -0.0000

Data Index: 157238 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.3501. Min Act: -0.0000

Data Index: 1896933 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1804039 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1235669 (The Pile)

Max Activating Token Index: 298

Text #13

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.3576. Min Act: -0.0000

Data Index: 1276956 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.2798. Min Act: -0.0000

Data Index: 1159663 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1739249 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.2564. Min Act: -0.0000

Data Index: 37391 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.2725. Min Act: -0.0000

Data Index: 953413 (The Pile)

Max Activating Token Index: 213

Text #18

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.3247. Min Act: -0.0000

Data Index: 1142749 (The Pile)

Max Activating Token Index: 648

Text #19

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.2401. Min Act: -0.0000

Data Index: 1208935 (The Pile)

Max Activating Token Index: 178