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

Dataset: The Pile

Neuron 4781 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: 5.3136. Min Range: -5.3136

Max Act: 5.3136. Min Act: -0.0000

Data Index: 89381 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.9561. Min Act: -0.0000

Data Index: 1067540 (The Pile)

Max Activating Token Index: 827

Text #2

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.8055. Min Act: -0.0000

Data Index: 138803 (The Pile)

Max Activating Token Index: 494

Text #3

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.9013. Min Act: -0.0000

Data Index: 830279 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.3547. Min Act: -0.0000

Data Index: 256415 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.8273. Min Act: -0.0000

Data Index: 36701 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.4359. Min Act: -0.0000

Data Index: 1090532 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.7553. Min Act: -0.0000

Data Index: 1123289 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.3735. Min Act: -0.0000

Data Index: 1237500 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.1377. Min Act: -0.0000

Data Index: 942029 (The Pile)

Max Activating Token Index: 738

Text #10

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.4374. Min Act: -0.0000

Data Index: 1284214 (The Pile)

Max Activating Token Index: 424

Text #11

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.6112. Min Act: -0.0000

Data Index: 1001110 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.4136. Min Act: -0.0000

Data Index: 1958318 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.4030. Min Act: -0.0000

Data Index: 1088653 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.4172. Min Act: -0.0000

Data Index: 409565 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.1955. Min Act: -0.0000

Data Index: 1507384 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.1457. Min Act: -0.0000

Data Index: 1322504 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.4835. Min Act: -0.0000

Data Index: 1259250 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.2388. Min Act: -0.0000

Data Index: 573582 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 5.3136. Min Range: -5.3136

Max Act: 3.7650. Min Act: -0.0000

Data Index: 996167 (The Pile)

Max Activating Token Index: 957