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

Dataset: The Pile

Neuron 2428 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3771. Min Act: -0.0000

Data Index: 818380 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.4137. Min Act: -0.0000

Data Index: 34613 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1127654 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3114. Min Act: -0.0000

Data Index: 311645 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1745520 (The Pile)

Max Activating Token Index: 559

Text #5

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1923698 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3256. Min Act: 0.0000

Data Index: 550661 (The Pile)

Max Activating Token Index: 385

Text #7

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1526767 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1311120 (The Pile)

Max Activating Token Index: 933

Text #9

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2988. Min Act: -0.0000

Data Index: 187261 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1169195 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2944. Min Act: -0.0000

Data Index: 77839 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3080. Min Act: -0.0000

Data Index: 397713 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1977665 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2742. Min Act: -0.0001

Data Index: 1671875 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1673070 (The Pile)

Max Activating Token Index: 993

Text #16

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2930. Min Act: 0.0000

Data Index: 1808889 (The Pile)

Max Activating Token Index: 581

Text #17

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2860. Min Act: -0.0000

Data Index: 11749 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2837. Min Act: -0.0000

Data Index: 447684 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1739219 (The Pile)

Max Activating Token Index: 666