Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3054 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.7236. Min Act: -0.0000

Data Index: 593796 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.4297. Min Act: -0.0000

Data Index: 629454 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.3681. Min Act: -0.0000

Data Index: 1097968 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.2505. Min Act: -0.0000

Data Index: 907422 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.3347. Min Act: -0.0000

Data Index: 1941163 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.3003. Min Act: -0.0000

Data Index: 1883851 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.2882. Min Act: -0.0000

Data Index: 824161 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1444486 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.4249. Min Act: -0.0000

Data Index: 761306 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.3336. Min Act: -0.0000

Data Index: 879624 (The Pile)

Max Activating Token Index: 631

Text #10

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.3822. Min Act: -0.0000

Data Index: 1161833 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.3774. Min Act: -0.0000

Data Index: 951939 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.3912. Min Act: -0.0000

Data Index: 313148 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.1530. Min Act: -0.0000

Data Index: 212212 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.2703. Min Act: -0.0000

Data Index: 856223 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1581065 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.0555. Min Act: -0.0000

Data Index: 48292 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.1281. Min Act: -0.0000

Data Index: 241354 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1833181 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.0181. Min Act: -0.0000

Data Index: 714749 (The Pile)

Max Activating Token Index: 799