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

Dataset: The Pile

Neuron 4827 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.6497. Min Act: -0.0000

Data Index: 1307103 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.6344. Min Act: -0.0000

Data Index: 1084452 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.5443. Min Act: -0.0000

Data Index: 2573 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.6447. Min Act: -0.0000

Data Index: 1849171 (The Pile)

Max Activating Token Index: 848

Text #4

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.5390. Min Act: -0.0000

Data Index: 429296 (The Pile)

Max Activating Token Index: 155

Text #5

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.5529. Min Act: -0.0000

Data Index: 343833 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.6284. Min Act: -0.0000

Data Index: 1399921 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.5288. Min Act: -0.0000

Data Index: 1655367 (The Pile)

Max Activating Token Index: 305

Text #8

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.5200. Min Act: -0.0000

Data Index: 1731850 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.5132. Min Act: -0.0000

Data Index: 848744 (The Pile)

Max Activating Token Index: 711

Text #10

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.4550. Min Act: -0.0000

Data Index: 896054 (The Pile)

Max Activating Token Index: 178

Text #11

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.4513. Min Act: -0.0000

Data Index: 1689026 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.4068. Min Act: -0.0000

Data Index: 1642557 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1465040 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1018102 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.3715. Min Act: -0.0000

Data Index: 604585 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1157348 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.3256. Min Act: -0.0000

Data Index: 1746480 (The Pile)

Max Activating Token Index: 498

Text #18

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.3471. Min Act: -0.0000

Data Index: 1488337 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.3508. Min Act: -0.0000

Data Index: 906837 (The Pile)

Max Activating Token Index: 120