Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3023 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.6584. Min Act: -0.0001

Data Index: 1313244 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1165694 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1760712 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5908. Min Act: -0.0001

Data Index: 1357871 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5822. Min Act: -0.0000

Data Index: 774614 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5702. Min Act: 0.0000

Data Index: 1169310 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1847089 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1287599 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5439. Min Act: 0.0000

Data Index: 681492 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1506498 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5150. Min Act: -0.0000

Data Index: 214025 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5248. Min Act: -0.0000

Data Index: 94342 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1847095 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1220320 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1997141 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5232. Min Act: -0.0000

Data Index: 84632 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1221963 (The Pile)

Max Activating Token Index: 516

Text #17

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5193. Min Act: -0.0000

Data Index: 1659748 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5140. Min Act: -0.0000

Data Index: 977302 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5108. Min Act: -0.0001

Data Index: 1069638 (The Pile)

Max Activating Token Index: 640