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

Dataset: The Pile

Neuron 3411 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: 1.2610. Min Range: -1.2610

Max Act: 1.2610. Min Act: -0.0000

Data Index: 1338209 (The Pile)

Max Activating Token Index: 658

Text #1

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1051806 (The Pile)

Max Activating Token Index: 552

Text #2

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1914036 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0146. Min Act: -0.0000

Data Index: 511022 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.9458. Min Act: -0.0000

Data Index: 703345 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1476884 (The Pile)

Max Activating Token Index: 7

Text #6

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1858599 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1105386 (The Pile)

Max Activating Token Index: 899

Text #8

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1464040 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1287095 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1850642 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.9072. Min Act: -0.0000

Data Index: 30762 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8498. Min Act: -0.0000

Data Index: 960902 (The Pile)

Max Activating Token Index: 538

Text #13

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1780220 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1268063 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8666. Min Act: -0.0000

Data Index: 403445 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.7941. Min Act: -0.0000

Data Index: 798448 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1387060 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8030. Min Act: -0.0000

Data Index: 266081 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.7811. Min Act: -0.0000

Data Index: 590656 (The Pile)

Max Activating Token Index: 564