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

Dataset: The Pile

Neuron 1352 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: 0.8662. Min Range: -0.8662

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1825481 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1263930 (The Pile)

Max Activating Token Index: 512

Text #2

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7367. Min Act: -0.0000

Data Index: 997189 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6011. Min Act: -0.0000

Data Index: 784355 (The Pile)

Max Activating Token Index: 698

Text #4

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5515. Min Act: -0.0000

Data Index: 897812 (The Pile)

Max Activating Token Index: 160

Text #5

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5677. Min Act: -0.0000

Data Index: 547632 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5306. Min Act: -0.0000

Data Index: 112993 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5188. Min Act: -0.0000

Data Index: 126934 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5399. Min Act: -0.0000

Data Index: 361021 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1390259 (The Pile)

Max Activating Token Index: 159

Text #10

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4894. Min Act: -0.0000

Data Index: 445036 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1717378 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4944. Min Act: -0.0000

Data Index: 780875 (The Pile)

Max Activating Token Index: 434

Text #13

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1822181 (The Pile)

Max Activating Token Index: 858

Text #14

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1480697 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4091. Min Act: -0.0000

Data Index: 176199 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4439. Min Act: -0.0000

Data Index: 713213 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1908807 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1236432 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5152. Min Act: -0.0000

Data Index: 368004 (The Pile)

Max Activating Token Index: 806