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

Dataset: The Pile

Neuron 393 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: 0.8236. Min Range: -0.8236

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1936852 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.7859. Min Act: -0.0000

Data Index: 714500 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6149. Min Act: -0.0000

Data Index: 837048 (The Pile)

Max Activating Token Index: 368

Text #3

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1194871 (The Pile)

Max Activating Token Index: 759

Text #4

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1852709 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1264148 (The Pile)

Max Activating Token Index: 173

Text #6

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1680072 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5833. Min Act: -0.0000

Data Index: 766695 (The Pile)

Max Activating Token Index: 985

Text #8

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5469. Min Act: -0.0000

Data Index: 438321 (The Pile)

Max Activating Token Index: 853

Text #9

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5649. Min Act: -0.0000

Data Index: 430607 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5423. Min Act: -0.0000

Data Index: 502369 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5170. Min Act: -0.0000

Data Index: 578001 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1770048 (The Pile)

Max Activating Token Index: 244

Text #13

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5258. Min Act: -0.0000

Data Index: 181002 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5419. Min Act: -0.0000

Data Index: 6589 (The Pile)

Max Activating Token Index: 912

Text #15

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5374. Min Act: -0.0000

Data Index: 301035 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5138. Min Act: -0.0000

Data Index: 276293 (The Pile)

Max Activating Token Index: 744

Text #17

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5140. Min Act: -0.0000

Data Index: 620480 (The Pile)

Max Activating Token Index: 486

Text #18

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1186505 (The Pile)

Max Activating Token Index: 321

Text #19

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5035. Min Act: -0.0000

Data Index: 573764 (The Pile)

Max Activating Token Index: 177