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

Dataset: The Pile

Neuron 1631 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3589. Min Range: -1.3589

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1294202 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1163390 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1373392 (The Pile)

Max Activating Token Index: 408

Text #3

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1947851 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.9137. Min Act: -0.0000

Data Index: 413580 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1455727 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1071449 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.7170. Min Act: -0.0000

Data Index: 874177 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1007781 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1096231 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1668885 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.7472. Min Act: -0.0000

Data Index: 733116 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.7145. Min Act: -0.0000

Data Index: 538979 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1803968 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1064056 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1331594 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1605986 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.6371. Min Act: -0.0000

Data Index: 518795 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.6343. Min Act: -0.0000

Data Index: 334014 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.6187. Min Act: -0.0000

Data Index: 670788 (The Pile)

Max Activating Token Index: 665