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

Dataset: The Pile

Neuron 695 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.9965. Min Act: -0.0000

Data Index: 968346 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.2851. Min Act: -0.0000

Data Index: 1082729 (The Pile)

Max Activating Token Index: 737

Text #2

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.6423. Min Act: -0.0000

Data Index: 201248 (The Pile)

Max Activating Token Index: 736

Text #3

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1674626 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1020770 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1275972 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1585345 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.8907. Min Act: -0.0000

Data Index: 787523 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1620345 (The Pile)

Max Activating Token Index: 394

Text #9

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1541133 (The Pile)

Max Activating Token Index: 248

Text #10

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.8417. Min Act: -0.0000

Data Index: 995140 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.8920. Min Act: -0.0000

Data Index: 884987 (The Pile)

Max Activating Token Index: 404

Text #12

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.7776. Min Act: -0.0000

Data Index: 972261 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.8104. Min Act: -0.0000

Data Index: 653231 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.7383. Min Act: -0.0000

Data Index: 144246 (The Pile)

Max Activating Token Index: 614

Text #15

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.8363. Min Act: -0.0000

Data Index: 935171 (The Pile)

Max Activating Token Index: 696

Text #16

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1275151 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.7788. Min Act: -0.0000

Data Index: 908241 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1867798 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 1.6423. Min Range: -1.6423

Max Act: 0.7957. Min Act: -0.0000

Data Index: 46388 (The Pile)

Max Activating Token Index: 276